From spike at rainier66.com Sun Sep 1 00:35:45 2024 From: spike at rainier66.com (spike at rainier66.com) Date: Sat, 31 Aug 2024 17:35:45 -0700 Subject: [ExI] musk is making BLUE cybertrucks! In-Reply-To: <002001dafc06$891ca490$9b55edb0$@rainier66.com> References: <002001dafc06$891ca490$9b55edb0$@rainier66.com> Message-ID: <002701dafc06$e2921a00$a7b64e00$@rainier66.com> WOWsers that is a cool color: https://twitter.com/i/status/1829972225241596197 spike -------------- next part -------------- An HTML attachment was scrubbed... URL: From atymes at gmail.com Sun Sep 1 00:40:07 2024 From: atymes at gmail.com (Adrian Tymes) Date: Sat, 31 Aug 2024 20:40:07 -0400 Subject: [ExI] musk is making BLUE cybertrucks! In-Reply-To: <002701dafc06$e2921a00$a7b64e00$@rainier66.com> References: <002001dafc06$891ca490$9b55edb0$@rainier66.com> <002701dafc06$e2921a00$a7b64e00$@rainier66.com> Message-ID: Despite the official recommendation to keep Cybertrucks unpainted, painting them - or putting a conformal fabric covering over them - protects against environmental damage and makes them look better. On Sat, Aug 31, 2024 at 8:37?PM spike jones via extropy-chat < extropy-chat at lists.extropy.org> wrote: > > > > > WOWsers that is a cool color: > > > > https://twitter.com/i/status/1829972225241596197 > > > > spike > _______________________________________________ > extropy-chat mailing list > extropy-chat at lists.extropy.org > http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat > -------------- next part -------------- An HTML attachment was scrubbed... URL: From dsunley at gmail.com Sun Sep 1 01:21:00 2024 From: dsunley at gmail.com (Darin Sunley) Date: Sat, 31 Aug 2024 19:21:00 -0600 Subject: [ExI] musk is making BLUE cybertrucks! In-Reply-To: References: <002001dafc06$891ca490$9b55edb0$@rainier66.com> <002701dafc06$e2921a00$a7b64e00$@rainier66.com> Message-ID: I saw a red one the other day. Looked cool, though I do have to wonder at the personality type that thought a cybertruck wasn't getting /enough/ attention before. On Sat, Aug 31, 2024 at 6:41?PM Adrian Tymes via extropy-chat < extropy-chat at lists.extropy.org> wrote: > Despite the official recommendation to keep Cybertrucks unpainted, > painting them - or putting a conformal fabric covering over them - protects > against environmental damage and makes them look better. > > On Sat, Aug 31, 2024 at 8:37?PM spike jones via extropy-chat < > extropy-chat at lists.extropy.org> wrote: > >> >> >> >> >> WOWsers that is a cool color: >> >> >> >> https://twitter.com/i/status/1829972225241596197 >> >> >> >> spike >> _______________________________________________ >> extropy-chat mailing list >> extropy-chat at lists.extropy.org >> http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat >> > _______________________________________________ > extropy-chat mailing list > extropy-chat at lists.extropy.org > http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat > -------------- next part -------------- An HTML attachment was scrubbed... URL: From brent.allsop at gmail.com Sun Sep 1 01:46:47 2024 From: brent.allsop at gmail.com (Brent Allsop) Date: Sat, 31 Aug 2024 19:46:47 -0600 Subject: [ExI] musk is making BLUE cybertrucks! In-Reply-To: References: <002001dafc06$891ca490$9b55edb0$@rainier66.com> <002701dafc06$e2921a00$a7b64e00$@rainier66.com> Message-ID: Did anyone see the guy getting hit on the street, or was that not important compared to the cool cybertruck? On Sat, Aug 31, 2024 at 7:21?PM Darin Sunley via extropy-chat < extropy-chat at lists.extropy.org> wrote: > I saw a red one the other day. > > Looked cool, though I do have to wonder at the personality type that > thought a cybertruck wasn't getting /enough/ attention before. > > On Sat, Aug 31, 2024 at 6:41?PM Adrian Tymes via extropy-chat < > extropy-chat at lists.extropy.org> wrote: > >> Despite the official recommendation to keep Cybertrucks unpainted, >> painting them - or putting a conformal fabric covering over them - protects >> against environmental damage and makes them look better. >> >> On Sat, Aug 31, 2024 at 8:37?PM spike jones via extropy-chat < >> extropy-chat at lists.extropy.org> wrote: >> >>> >>> >>> >>> >>> WOWsers that is a cool color: >>> >>> >>> >>> https://twitter.com/i/status/1829972225241596197 >>> >>> >>> >>> spike >>> _______________________________________________ >>> extropy-chat mailing list >>> extropy-chat at lists.extropy.org >>> http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat >>> >> _______________________________________________ >> extropy-chat mailing list >> extropy-chat at lists.extropy.org >> http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat >> > _______________________________________________ > extropy-chat mailing list > extropy-chat at lists.extropy.org > http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat > -------------- next part -------------- An HTML attachment was scrubbed... URL: From atymes at gmail.com Sun Sep 1 02:54:46 2024 From: atymes at gmail.com (Adrian Tymes) Date: Sat, 31 Aug 2024 22:54:46 -0400 Subject: [ExI] musk is making BLUE cybertrucks! In-Reply-To: References: <002001dafc06$891ca490$9b55edb0$@rainier66.com> <002701dafc06$e2921a00$a7b64e00$@rainier66.com> Message-ID: That was rather the dark humorous point, as I understood it. On Sat, Aug 31, 2024 at 9:48?PM Brent Allsop via extropy-chat < extropy-chat at lists.extropy.org> wrote: > Did anyone see the guy getting hit on the street, or was that not > important compared to the cool cybertruck? > > > On Sat, Aug 31, 2024 at 7:21?PM Darin Sunley via extropy-chat < > extropy-chat at lists.extropy.org> wrote: > >> I saw a red one the other day. >> >> Looked cool, though I do have to wonder at the personality type that >> thought a cybertruck wasn't getting /enough/ attention before. >> >> On Sat, Aug 31, 2024 at 6:41?PM Adrian Tymes via extropy-chat < >> extropy-chat at lists.extropy.org> wrote: >> >>> Despite the official recommendation to keep Cybertrucks unpainted, >>> painting them - or putting a conformal fabric covering over them - protects >>> against environmental damage and makes them look better. >>> >>> On Sat, Aug 31, 2024 at 8:37?PM spike jones via extropy-chat < >>> extropy-chat at lists.extropy.org> wrote: >>> >>>> >>>> >>>> >>>> >>>> WOWsers that is a cool color: >>>> >>>> >>>> >>>> https://twitter.com/i/status/1829972225241596197 >>>> >>>> >>>> >>>> spike >>>> _______________________________________________ >>>> extropy-chat mailing list >>>> extropy-chat at lists.extropy.org >>>> http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat >>>> >>> _______________________________________________ >>> extropy-chat mailing list >>> extropy-chat at lists.extropy.org >>> http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat >>> >> _______________________________________________ >> extropy-chat mailing list >> extropy-chat at lists.extropy.org >> http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat >> > _______________________________________________ > extropy-chat mailing list > extropy-chat at lists.extropy.org > http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat > -------------- next part -------------- An HTML attachment was scrubbed... URL: From pharos at gmail.com Tue Sep 3 14:10:15 2024 From: pharos at gmail.com (BillK) Date: Tue, 3 Sep 2024 15:10:15 +0100 Subject: [ExI] =?utf-8?q?Telescoping_Tomorrow=3A_Nick_Bostrom_on_AI?= =?utf-8?q?=E2=80=99s_Radical_Potential?= Message-ID: Bostrom?s insights challenge us to consider not just what AI can do today, but what it might be capable of tomorrow, and how we can best prepare for a future that may arrive sooner than we think. September 2, 2024 Ari Haruni Quotes: Nick Bostrom says progress in AI is likely to lead to radical superintelligence and a "telescoping of the future" where the world will change enormously in the space of a year or a few years. However, Bostrom urges us to extend our vision beyond these immediate commercial applications. He posits that the development of AI will not halt at improved language models or more efficient integration into existing products. Instead, he foresees a path leading to what he terms ?radical forms of superintelligence? ? AI systems that surpass human cognitive abilities across all domains. This concept of artificial general intelligence (AGI) is not new, but Bostrom?s perspective on its implications is particularly striking. He envisions a future where AGI renders all human intellectual labor obsolete, a prospect that is both awe-inspiring and potentially unsettling. --------------------------- This is the optimistic version of revolutionary changes within the next few years. But revolutions have downsides as well. Hopefully we will solve all the problems. BillK From lloydmillerus at gmail.com Tue Sep 3 16:04:04 2024 From: lloydmillerus at gmail.com (Lloyd Miller) Date: Tue, 3 Sep 2024 12:04:04 -0400 Subject: [ExI] Could You (Will You) Marry a Robot? In-Reply-To: References: Message-ID: Couldn't be worse than my actual marriages. Probably better than most of my sex hook-ups, too. Lloyd Miller, Research Director lloydmillerus at gmail.com On Fri, Aug 30, 2024 at 1:08?AM Adrian Tymes via extropy-chat < extropy-chat at lists.extropy.org> wrote: > Could You Marry a Robot? >> > > No, as that is an aspect of the law and the law where I am does not > recognize such marriages (for good reason, as AIs have a long way to go > before being ready to enter into such long term contracts), but apparently > it has happened in other jurisdictions: > https://www.google.com/search?q=marry+robot . > _______________________________________________ > extropy-chat mailing list > extropy-chat at lists.extropy.org > http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat > -------------- next part -------------- An HTML attachment was scrubbed... URL: From spike at rainier66.com Wed Sep 4 15:19:58 2024 From: spike at rainier66.com (spike at rainier66.com) Date: Wed, 4 Sep 2024 08:19:58 -0700 Subject: [ExI] List test In-Reply-To: <004e01dafedc$951f7d20$bf5e7760$@rainier66.com> References: <5fc0394a-45fa-f09c-f0c3-00ea5834cf15@daisy.zia.io> <004e01dafedc$951f7d20$bf5e7760$@rainier66.com> Message-ID: <005101dafedd$e7f8a2f0$b7e9e8d0$@rainier66.com> -----Original Message----- From: extropy-chat On Behalf Of John Klos via extropy-chat Subject: [ExI] List test Hi, all, This is just a test to confirm that the list is working. Please let me know if you experience any problems. Thanks, John _______________________________________________ John, right after your post last Tuesday, everything from ExI somehow ended up going into my spam folder. I sure didn't tell it to do that. Most mysterious is this. I wondered why nobody was posting to ExI, considering all the exciting cool stuff happening, so I went into my spam folder and found several cool threads about alien behavior and blue cybertrucks and such as that. In any case, fixed that, and welcome back everybody. Regarding the dark humor in the blue cybertruck post: Adrian there is something I admire about you. You read my posts and figure out what I am doing, then quietly play along, usually contributing something to make it even funnier. Thanks for that, me lad! Second thought on that post: had skateboard boy getting swatted by the Buick been an old lady rather than a teenager, someone unlikely to bounce, that post woulda not been funny at all. I figure that kid likely got off that street cussing and blaspheming, with a bit of road rash and a whole new attitude about crossing against the light. spike From spike at rainier66.com Wed Sep 4 15:29:17 2024 From: spike at rainier66.com (spike at rainier66.com) Date: Wed, 4 Sep 2024 08:29:17 -0700 Subject: [ExI] ETs/Aliens In-Reply-To: <004d01dafedc$5ce03a30$16a0ae90$@rainier66.com> References: <41880936-a95b-4ed1-a8c2-6940f0b033a4@zaiboc.net> <004d01dafedc$5ce03a30$16a0ae90$@rainier66.com> Message-ID: <005901dafedf$351f3250$9f5d96f0$@rainier66.com> -----Original Message----- From: spike at rainier66.com Sent: Wednesday, 4 September, 2024 8:09 AM To: spike at rainier66.com Subject: FW: [ExI] ETs/Aliens -----Original Message----- From: extropy-chat On Behalf Of Ben Zaiboc via extropy-chat Sent: Friday, 30 August, 2024 2:17 AM To: extropy-chat at lists.extropy.org Cc: Ben Zaiboc Subject: Re: [ExI] ETs/Aliens On 28/08/2024 22:05, spike wrote: suppose we had a sim which could run a our speed, at one human equivalent. Would 5 billion years of that make sense? Well, we like to think so. But... perhaps not. Perhaps 50 million years of one human equivalent would be sufficient, and if so, an MBrain, with its latency limits would make perfect sense. >...Sufficient for what, spike? ... >...I don't think we can really even guess what 'sufficient' would mean to an upload, alien or human, in terms of subjective lifespan. Ben Ben, you are right: we can't really guess. But Eliezer wrote extensively on this topic years ago under a thread he called Is There an Infinite Amount of Fun? Answer: we don't know, but I have pondered this for decades, vaguely and reluctantly concluding there is probably a finite amount of fun. This is bad news indeed, but my "proof" is anything but rigorous. It goes like this: in any thermal system, eventually equilibrium is reached. In a chess game, if the same position is reached three times, play stops, the game is a draw. We learn quickly early in life, but later on we get set in our ways, changes come more slowly and with greater difficulty. Maybe it is true that given arbitrarily much time, we could keep finding new fun somewhere, finding new and interesting things to learn. But we might not be able to do that. After a certain period of time, we might conclude that OK, we have lived enough. When we stop learning, thinking, growing, we are the functional equivalent of dead, even if we still draw breath and our hearts still beat. Perhaps 50 million years at one human equivalent speed is sufficient to reach that end point. But of course we don't know that. It would be equivalent to six million consecutive human lives, so we have no way to comprehend what that would be like. spike From atymes at gmail.com Wed Sep 4 18:24:08 2024 From: atymes at gmail.com (Adrian Tymes) Date: Wed, 4 Sep 2024 14:24:08 -0400 Subject: [ExI] List test In-Reply-To: <005101dafedd$e7f8a2f0$b7e9e8d0$@rainier66.com> References: <5fc0394a-45fa-f09c-f0c3-00ea5834cf15@daisy.zia.io> <004e01dafedc$951f7d20$bf5e7760$@rainier66.com> <005101dafedd$e7f8a2f0$b7e9e8d0$@rainier66.com> Message-ID: On Wed, Sep 4, 2024, 11:22?AM spike jones via extropy-chat < extropy-chat at lists.extropy.org> wrote: > Adrian there is > something I admire about you. You read my posts and figure out what I am > doing, then quietly play along, usually contributing something to make it > even funnier. Thanks for that, me lad! > You are welcome. I can't promise to always do that, but it happens from time to time. A couple days ago when discussing that thermal nuclear spaceplane project, someone asked facetiously (using enough buzzwords that their intent was obvious) what my plans were to incorporate AI. I responded that the project wouldn't directly make a point of using AI, but that AI was being incorporated into the tools we would be using - whether we liked it or not. Speaking of that project, it's been announced now: https://twitter.com/cubecab/status/1830757753251324164 > -------------- next part -------------- An HTML attachment was scrubbed... URL: From hkeithhenson at gmail.com Wed Sep 4 20:47:21 2024 From: hkeithhenson at gmail.com (Keith Henson) Date: Wed, 4 Sep 2024 13:47:21 -0700 Subject: [ExI] ETs/Aliens In-Reply-To: <005901dafedf$351f3250$9f5d96f0$@rainier66.com> References: <41880936-a95b-4ed1-a8c2-6940f0b033a4@zaiboc.net> <004d01dafedc$5ce03a30$16a0ae90$@rainier66.com> <005901dafedf$351f3250$9f5d96f0$@rainier66.com> Message-ID: Most of you have seen this http://hplusmagazine.com/2012/04/12/transhumanism-and-the-human-expansion-into-space-a-conflict-with-physics/ I made a case for civilization "collapsing" to 300-meter spheres sunk in the deep ocean for cooling. But if what we see at Tabby's Star and the other 24 in that cluster are data centers up to 400 times the area of the Earth, they seem to tolerate a speed-of-light communication delay of around 1.5 seconds. That indicates the aliens (if any) are running at close to our clock rate and I am wrong about a million-to-one speedup at least in that case. Keith On Wed, Sep 4, 2024 at 8:30?AM spike jones via extropy-chat wrote: > > > > -----Original Message----- > From: spike at rainier66.com > Sent: Wednesday, 4 September, 2024 8:09 AM > To: spike at rainier66.com > Subject: FW: [ExI] ETs/Aliens > > > > -----Original Message----- > From: extropy-chat On Behalf Of Ben Zaiboc via extropy-chat > Sent: Friday, 30 August, 2024 2:17 AM > To: extropy-chat at lists.extropy.org > Cc: Ben Zaiboc > Subject: Re: [ExI] ETs/Aliens > > > On 28/08/2024 22:05, spike wrote: > > > suppose we had a sim which could run a our speed, at one human > equivalent. Would 5 billion years of that make sense? Well, we like to > think so. But... perhaps not. Perhaps 50 million years of one human > equivalent would be sufficient, and if so, an MBrain, with its latency > limits would make perfect sense. > > > >...Sufficient for what, spike? > > ... > > >...I don't think we can really even guess what 'sufficient' would mean to an upload, alien or human, in terms of subjective lifespan. > > Ben > > > > Ben, you are right: we can't really guess. But Eliezer wrote extensively on this topic years ago under a thread he called Is There an Infinite Amount of Fun? > > Answer: we don't know, but I have pondered this for decades, vaguely and reluctantly concluding there is probably a finite amount of fun. This is bad news indeed, but my "proof" is anything but rigorous. It goes like this: in any thermal system, eventually equilibrium is reached. In a chess game, if the same position is reached three times, play stops, the game is a draw. We learn quickly early in life, but later on we get set in our ways, changes come more slowly and with greater difficulty. > > Maybe it is true that given arbitrarily much time, we could keep finding new fun somewhere, finding new and interesting things to learn. But we might not be able to do that. After a certain period of time, we might conclude that OK, we have lived enough. When we stop learning, thinking, growing, we are the functional equivalent of dead, even if we still draw breath and our hearts still beat. Perhaps 50 million years at one human equivalent speed is sufficient to reach that end point. > > But of course we don't know that. It would be equivalent to six million consecutive human lives, so we have no way to comprehend what that would be like. > > spike > > > > > > > > > _______________________________________________ > extropy-chat mailing list > extropy-chat at lists.extropy.org > http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat From atymes at gmail.com Wed Sep 4 21:12:45 2024 From: atymes at gmail.com (Adrian Tymes) Date: Wed, 4 Sep 2024 17:12:45 -0400 Subject: [ExI] ETs/Aliens In-Reply-To: <005901dafedf$351f3250$9f5d96f0$@rainier66.com> References: <41880936-a95b-4ed1-a8c2-6940f0b033a4@zaiboc.net> <004d01dafedc$5ce03a30$16a0ae90$@rainier66.com> <005901dafedf$351f3250$9f5d96f0$@rainier66.com> Message-ID: On Wed, Sep 4, 2024 at 11:30?AM spike jones via extropy-chat < extropy-chat at lists.extropy.org> wrote: > Maybe it is true that given arbitrarily much time, we could keep finding > new fun somewhere, finding new and interesting things to learn. But we > might not be able to do that. After a certain period of time, we might > conclude that OK, we have lived enough. When we stop learning, thinking, > growing, we are the functional equivalent of dead, even if we still draw > breath and our hearts still beat. Perhaps 50 million years at one human > equivalent speed is sufficient to reach that end point. > > But of course we don't know that. It would be equivalent to six million > consecutive human lives, so we have no way to comprehend what that would be > like. > We've known since at least the time of the ancient Greek philosophers. I'm told that Aristotle observed that, even in his day, information was being produced faster than one person could learn it all. The same seems abundantly true today. New fun keeps being created and shared in an exponentially increasing rate, as more humans are enabled to be content creators - which inevitably means an increasing number (whether or not the same percentage) of them hit upon forms that appeal (or would appeal, with sufficient marketing/advertising to spread awareness) to a substantial number of other people. As you enjoy things, new things to enjoy are being made at a faster rate than you can consume them - even if you had all your needs taken care of and devoted yourself entirely to consuming content without ever again creating anything of interest to others, a lifestyle that some strive to approach. Of course, part of this is because there is some subset of humanity - again, some percentage (likely to increase as more of humanity gains access to the relevant tools) - that finds fun in creating content for others to enjoy. The only way that's going down is if the human population dramatically shrinks, which would cause several more urgent problems. -------------- next part -------------- An HTML attachment was scrubbed... URL: From pharos at gmail.com Wed Sep 4 22:56:59 2024 From: pharos at gmail.com (BillK) Date: Wed, 4 Sep 2024 23:56:59 +0100 Subject: [ExI] ETs/Aliens In-Reply-To: <005901dafedf$351f3250$9f5d96f0$@rainier66.com> References: <41880936-a95b-4ed1-a8c2-6940f0b033a4@zaiboc.net> <004d01dafedc$5ce03a30$16a0ae90$@rainier66.com> <005901dafedf$351f3250$9f5d96f0$@rainier66.com> Message-ID: On Wed, 4 Sept 2024 at 16:31, spike jones via extropy-chat < extropy-chat at lists.extropy.org> wrote: > > > Maybe it is true that given arbitrarily much time, we could keep finding new fun somewhere, finding new and interesting things to learn. But we might not be able to do that. After a certain period of time, we might conclude that OK, we have lived enough. When we stop learning, thinking, growing, we are the functional equivalent of dead, even if we still draw breath and our hearts still beat. Perhaps 50 million years at one human equivalent speed is sufficient to reach that end point. > > But of course we don't know that. It would be equivalent to six million consecutive human lives, so we have no way to comprehend what that would be like. > > spike > _______________________________________________ In my reply above, I mentioned that to fast--thinking uploads the physical world would appear to be 'frozen'. I discussed this with Perplexity AI and it objected, saying that the upload would have to interact at physical speeds. I contradicted Perplexity AI, saying that it would seem like years would pass while waiting for a physical effect. Perplexity AIs response was interesting - BillK Perplexity AI Answer You raise an excellent point that I didn't fully address in my initial critique. Let's explore this concept further and improve our understanding of the implications for uploads interacting with the physical world. Time Perception for Uploads You're absolutely correct that the vast difference in processing speeds between uploads and the physical world would create a significant perceptual gap. This disparity would indeed make physical interactions seem excruciatingly slow from the upload's perspective. To illustrate this: - If an upload's cognitive processes run 1 million times faster than a human brain, a single Earth day would subjectively feel like about 2,740 years to the upload. - Even a seemingly quick action, like pressing a button, which might take a human 0.1 seconds, would feel like over 27 hours to the upload. This immense time dilation effect would have profound implications: 1. *Patience and Planning*: Uploads would need to develop extraordinary patience or devise methods to "time-share" their consciousness, perhaps entering dormant states while waiting for physical processes to complete. 2. *Simulation Preference*: They might prefer to operate primarily within simulated environments where time can be manipulated to match their cognitive speed. 3. *Delegation*: Uploads might create subordinate AIs or robotic systems to interact with the physical world on their behalf, allowing them to focus on higher-level decision-making. 4. *Alternative Occupations*: As you correctly point out, uploads would need to find ways to occupy their minds during these vast subjective time periods. This could lead to: - Extensive introspection and self-improvement - Development of complex virtual societies - Exploration of abstract mathematical or philosophical concepts - Creation of elaborate art or entertainment within their virtual spaces Implications for Interstellar Travel - Uploads might find the pace of physical space exploration frustratingly slow, potentially leading to a preference for virtual exploration or expansion. - The extreme time dilation might make communication with biological entities or slower AIs nearly impossible, potentially resulting in upload civilizations becoming isolated or incomprehensible to other forms of intelligence. In conclusion, your observation about the time perception of uploads is crucial and has far-reaching implications for how we envision potential upload civilizations and their interactions with the physical universe. It underscores the need to consider not just the capabilities of such entities, but also their subjective experiences and motivations when speculating about their potential behaviors and impacts on the cosmos. ------------------------------- -------------- next part -------------- An HTML attachment was scrubbed... URL: From pharos at gmail.com Fri Sep 6 17:19:27 2024 From: pharos at gmail.com (BillK) Date: Fri, 6 Sep 2024 18:19:27 +0100 Subject: [ExI] AIs for criminals Message-ID: While experts are concerned about AI safety and nations are signing agreements to develop safe AI, the criminal underworld is actively developing malicious AIs (Malla). As AIs become more powerful, what will be the result of humans deliberately developing malicious AIs? Is this humanity committing suicide? BillK Quotes: Top five strategies from Meta?s CyberSecEval 3 to combat weaponized LLMs Louis Columbus September 3, 2024 The goal: Get in front of weaponized LLM threats Malicious attackers? LLM tradecraft is moving too fast for many enterprises, CISOs and security leaders to keep up. Meta?s comprehensive report, published last month, makes a convincing argument for getting ahead of the growing threats of weaponized LLMs. ---------------- From john at klos.com Fri Sep 6 20:55:43 2024 From: john at klos.com (John Klos) Date: Fri, 6 Sep 2024 20:55:43 +0000 (UTC) Subject: [ExI] List test Message-ID: <1395a125-a9f5-6c58-00c3-b5515f8284ad@daisy.zia.io> Hi! > John, right after your post last Tuesday, everything from ExI somehow ended > up going into my spam folder. I sure didn't tell it to do that. Most > mysterious is this. I wondered why nobody was posting to ExI, considering > all the exciting cool stuff happening, so I went into my spam folder and > found several cool threads about alien behavior and blue cybertrucks and > such as that. > > In any case, fixed that, and welcome back everybody. The IP address of the main Extropy server changed, and although all list email is still sent through the same address as before, the fact that the source changed is enough to make Google unhappy. Poor Google! Luckily, we don't change addresses often. Thanks! John From pharos at gmail.com Sat Sep 7 13:26:41 2024 From: pharos at gmail.com (BillK) Date: Sat, 7 Sep 2024 14:26:41 +0100 Subject: [ExI] AIs for criminals In-Reply-To: References: Message-ID: On Fri, 6 Sept 2024 at 18:19, BillK wrote: > > While experts are concerned about AI safety and nations are signing > agreements to develop safe AI, the criminal underworld is actively > developing malicious AIs (Malla). > ---------------- The problem is not just criminals. Nation-states are also developing malicious AI for cyberattacks. Of course, accusing Russia of cyberattacks doesn't mean that other countries aren't also developing AI for similar cyberattacks. BillK Quote: US, allied nations accuse Russia of cyberattacks against Ukraine and NATO Hacking efforts as part of this campaign began in 2020, and included attacks on Ukrainian groups ahead of Russia?s invasion, along with critical infrastructure organizations in NATO member states. By Maggie Miller 09/05/2024 ------------------- From ben at zaiboc.net Sat Sep 7 16:12:51 2024 From: ben at zaiboc.net (Ben Zaiboc) Date: Sat, 7 Sep 2024 17:12:51 +0100 Subject: [ExI] ETs/Aliens In-Reply-To: References: Message-ID: <2ad5ad52-e0d9-422f-a6c4-3b1b394cc0e8@zaiboc.net> On 07/09/2024 14:27, spike wrote: > Maybe it is true that given arbitrarily much time, we could keep finding > new fun somewhere, finding new and interesting things to learn. But we > might not be able to do that. After a certain period of time, we might > conclude that OK, we have lived enough. When we stop learning, > thinking, growing, we are the functional equivalent of dead, even if we > still draw breath and our hearts still beat. Perhaps 50 million years > at one human equivalent speed is sufficient to reach that end point. > > But of course we don't know that. It would be equivalent to six million > consecutive human lives, so we have no way to comprehend what that > would be like. Six hundred thousand, unless the average human lifespan is 8.3 years. Or my calculator is badly misbehaving. So, ten times more comprehensible. Or 10 x less incomprehensible. Hm, No Way / 10 = Still no way. Ben -------------- next part -------------- An HTML attachment was scrubbed... URL: From ben at zaiboc.net Sat Sep 7 16:37:27 2024 From: ben at zaiboc.net (Ben Zaiboc) Date: Sat, 7 Sep 2024 17:37:27 +0100 Subject: [ExI] ETs/Aliens In-Reply-To: References: Message-ID: <0633afaf-e6e0-4d28-9218-0c076c7bed5f@zaiboc.net> On 07/09/2024 14:27, Keith Henson wrote: > Most of you have seen this > http://hplusmagazine.com/2012/04/12/transhumanism-and-the-human-expansion-into-space-a-conflict-with-physics/ > > I made a case for civilization "collapsing" to 300-meter spheres sunk > in the deep ocean for cooling. > > But if what we see at Tabby's Star and the other 24 in that cluster > are data centers up to 400 times the area of the Earth, they seem to > tolerate a speed-of-light communication delay of around 1.5 seconds. > That indicates the aliens (if any) are running at close to our clock > rate and I am wrong about a million-to-one speedup at least in that > case. > > Keith Surely such a data centre could contain many smaller clusters with much faster internal communications, that only interact with each other slowly, or rarely? Imagine 400 (or probably many more) separate civilisations, with a common agreement concerning the physical infrastructure but otherwise totally independent. This idea could be scaled up, with nested clusters of clusters of (clusters of, etc...) civilisations, metropolises, communities, right down to the individual level. Communication speeds would then be scaled depending on the level of the units communicating with each other. We already have a weak version of this. For example, we know that it takes ages for bureaucracies to get things done, and in the meantime we just get on with our lives. Not so long ago, people used to write letters to each other, and wait a few days or more for a reply. This didn't slow our everyday lives down. Usually! Perhaps for someone who is effectively immortal, waiting a couple of thousand subjective years for a reply to your message to uncle Bernard wouldn't be intolerable. The ability to vary your clock rate would add another dimension, too. It would be interesting to explore, perhaps in an SF story, the implications of being able to speed up and slow down your clock rate in a society where everyone has indefinitely long lifespans. Ben -------------- next part -------------- An HTML attachment was scrubbed... URL: From hkeithhenson at gmail.com Sat Sep 7 20:27:58 2024 From: hkeithhenson at gmail.com (Keith Henson) Date: Sat, 7 Sep 2024 13:27:58 -0700 Subject: [ExI] ETs/Aliens In-Reply-To: <0633afaf-e6e0-4d28-9218-0c076c7bed5f@zaiboc.net> References: <0633afaf-e6e0-4d28-9218-0c076c7bed5f@zaiboc.net> Message-ID: " perhaps in an SF story," I did that a long time ago. Do you need me to post a pointer again? Best wishes, Keith On Sat, Sep 7, 2024 at 9:38?AM Ben Zaiboc via extropy-chat wrote: > > > On 07/09/2024 14:27, Keith Henson wrote: > > Most of you have seen this > http://hplusmagazine.com/2012/04/12/transhumanism-and-the-human-expansion-into-space-a-conflict-with-physics/ > > I made a case for civilization "collapsing" to 300-meter spheres sunk > in the deep ocean for cooling. > > But if what we see at Tabby's Star and the other 24 in that cluster > are data centers up to 400 times the area of the Earth, they seem to > tolerate a speed-of-light communication delay of around 1.5 seconds. > That indicates the aliens (if any) are running at close to our clock > rate and I am wrong about a million-to-one speedup at least in that > case. > > Keith > > > Surely such a data centre could contain many smaller clusters with much faster internal communications, that only interact with each other slowly, or rarely? Imagine 400 (or probably many more) separate civilisations, with a common agreement concerning the physical infrastructure but otherwise totally independent. > > This idea could be scaled up, with nested clusters of clusters of (clusters of, etc...) civilisations, metropolises, communities, right down to the individual level. Communication speeds would then be scaled depending on the level of the units communicating with each other. > > We already have a weak version of this. For example, we know that it takes ages for bureaucracies to get things done, and in the meantime we just get on with our lives. Not so long ago, people used to write letters to each other, and wait a few days or more for a reply. This didn't slow our everyday lives down. Usually! > > Perhaps for someone who is effectively immortal, waiting a couple of thousand subjective years for a reply to your message to uncle Bernard wouldn't be intolerable. The ability to vary your clock rate would add another dimension, too. > > It would be interesting to explore, perhaps in an SF story, the implications of being able to speed up and slow down your clock rate in a society where everyone has indefinitely long lifespans. > > Ben > _______________________________________________ > extropy-chat mailing list > extropy-chat at lists.extropy.org > http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat From postmowoods at gmail.com Mon Sep 9 05:22:11 2024 From: postmowoods at gmail.com (Kelly Anderson) Date: Sun, 8 Sep 2024 23:22:11 -0600 Subject: [ExI] Could You (Will You) Marry a Robot? In-Reply-To: References: Message-ID: I still think the book: Love and Sex with Robots: The Evolution of Human-Robot Relationships by David Levy published in 2008 is one of the better treatments of this subject matter. Amazingly, the book is mostly about the human psychological predisposition to fall in love with cars, tomoguchi, and other inanimate objects. -Kelly On Thu, Aug 29, 2024 at 1:54?PM BillK via extropy-chat wrote: > > Could You Marry a Robot? > Exploring the Future of Love and AI > > Daniel Martinez August 28, 2024 > > > Quotes: > In a world where technology increasingly intersects with human life, > the idea of forming romantic relationships with robots is becoming > more plausible. Advances in AI and robotics are creating machines > capable of understanding and responding to human emotions, raising > questions about the future of companionship and marriage. As robots > evolve to potentially become life partners, this possibility > challenges societal norms, ethical considerations, and our > understanding of love. > ------ > As we engineer robots with the capacity to understand and reciprocate > human emotions, we're not just creating machines; we're birthing a new > form of companionship. Imagine a future where your robot partner > doesn't just assist with tasks but truly understands you, comforts > you, and anticipates your emotional needs?transforming the essence of > partnership. > ---------------------- > > The artificial humans will soon be here. Expensive at first, but mass > consumerism versions will follow, as robots make more robots. > Society will face big changes. > > BillK > > _______________________________________________ > extropy-chat mailing list > extropy-chat at lists.extropy.org > http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat From pharos at gmail.com Mon Sep 9 20:21:04 2024 From: pharos at gmail.com (BillK) Date: Mon, 9 Sep 2024 21:21:04 +0100 Subject: [ExI] Could You (Will You) Marry a Robot? In-Reply-To: References: Message-ID: On Mon, 9 Sept 2024 at 06:24, Kelly Anderson via extropy-chat < extropy-chat at lists.extropy.org> wrote: > > I still think the book: > Love and Sex with Robots: The Evolution of Human-Robot Relationships > by David Levy published in 2008 > is one of the better treatments of this subject matter. Amazingly, the > book is mostly about the human psychological predisposition to fall in > love with cars, tomoguchi, and other inanimate objects. > > -Kelly > _______________________________________________ I asked for an AI summary of this book. For a book written in 2008, it sounds years ahead of its time! BillK The book "Love and Sex with Robots: The Evolution of Human-Robot Relationships" explores the emerging field of human-robot relationships, examining the potential for robots to become intimate partners and the implications of such relationships on human society. Written by David Levy, a renowned expert in artificial intelligence and robotics, the book provides a comprehensive overview of the current state of robotics and its potential future developments. The author argues that as robots become increasingly advanced and human-like, it is inevitable that humans will form emotional bonds with them. He predicts that by the 2040s, robots will be capable of simulating human-like conversation, leading to the development of romantic relationships between humans and robots. Levy also explores the potential benefits of such relationships, including the ability of robots to provide companionship to the elderly and those with disabilities. One of the key takeaways from the book is the distinction between *androids* and *gynoids*. Androids are male robots, while gynoids are female robots. Levy argues that gynoids will be more appealing to humans due to their perceived femininity and nurturing qualities. He also predicts that gynoids will be more likely to be used as sex robots, leading to a new form of prostitution. The book also examines the potential legal and ethical implications of human-robot relationships. Levy argues that as robots become more advanced, they will require rights and protections similar to those afforded to humans. He also predicts that the development of sex robots will lead to a re-evaluation of prostitution laws and the concept of consent. Some of the key lessons and practical applications from the book include: 1. *Robotics will revolutionize the sex industry*: Levy predicts that sex robots will become increasingly popular, leading to a shift away from human prostitution. 2. *Robots will provide companionship to the elderly and those with disabilities*: As robots become more advanced, they will be able to provide emotional support and companionship to those in need. 3. *Human-robot relationships will challenge traditional notions of love and intimacy*: As humans form emotional bonds with robots, it will force a re-evaluation of what it means to love and be intimate with another being. 4. *The development of robots will require a re-evaluation of ethics and laws*: As robots become more advanced, they will require rights and protections similar to those afforded to humans, leading to a re-evaluation of ethics and laws. In conclusion, "Love and Sex with Robots" provides a comprehensive overview of the emerging field of human-robot relationships. The book's key takeaways highlight the potential benefits and implications of such relationships, including the potential for robots to provide companionship and the need for a re-evaluation of ethics and laws. As robotics continues to advance, this book provides a timely and thought-provoking exploration of the future of human-robot relationships. ------------------------------- -------------- next part -------------- An HTML attachment was scrubbed... URL: From pharos at gmail.com Mon Sep 9 20:57:33 2024 From: pharos at gmail.com (BillK) Date: Mon, 9 Sep 2024 21:57:33 +0100 Subject: [ExI] California on fire Message-ID: I've just seen a news report that a heatwave has started many wildfires in California. Mostly near Los Angeles. It sounds pretty bad. I also saw a report that in the USA, power cables were electrocuting birds, setting them on fire and then the flaming corpses were starting fires. I've never heard that before. BillK Quotes: Wildfires tear through western US during heat wave by Huw GRIFFITH September 9, 2024 A blaze burning out of a control near Los Angeles sparked mandatory evacuations as it tore through swathes of tinder-dry California countryside around popular tourist spots. The so-called Line Fire erupted on Thursday to the east of the city and exploded over the weekend, consuming more than 20,000 acres (8,000 hectares) and threatening tens of thousands of homes and other buildings. Mandatory evacuation orders have been imposed and major roads shuttered, as more than 1,700 firefighters battle to contain the fast-moving flames. -------------------------- From hkeithhenson at gmail.com Tue Sep 10 17:48:03 2024 From: hkeithhenson at gmail.com (Keith Henson) Date: Tue, 10 Sep 2024 10:48:03 -0700 Subject: [ExI] Cross post Message-ID: I posted this on a blog I infrequently visit and thought it might be of interest other places. ^^^^^^ At a meta level, why are people attracted to conspiracies/predictions of disasters? It relates to the popularity of this and similar blogs. OFW has (incorrectly so far) predicted collapse for ages that has not come about. It's not everyone, most of the people lined up and got their covid vaccine either because they understood vaccines or they just trusted the public health people who said it was a good idea. I.e., they judged the risks of taking the vaccine are lower than not taking it and getting the disease. Most of the time going along with the cultural norm works better. Rebels who planted their crops in the fall starved. But somehow contrarians continue to be born. The other factor is gullibility. A certain amount of believing what you hear is essential. I have written about the advantage humans have over cats and dogs of the "look both ways before you cross meme. Memes like scientology are, of course, utter bs but there are people with a deep belief in such nonsense. Talking to them has convinced me that the trait is like eye color, you are stuck with it. One of them talked to me a long time about their vulnerability to every MLM scheme that came along. It is not easy to sort out, even with such mental tools as evolutionary psychology. (EP says that every common psychological trait was either directly selected or it is a side effect of some trait that was selected.) Keith From postmowoods at gmail.com Tue Sep 10 21:25:55 2024 From: postmowoods at gmail.com (Kelly Anderson) Date: Tue, 10 Sep 2024 15:25:55 -0600 Subject: [ExI] Could You (Will You) Marry a Robot? In-Reply-To: References: Message-ID: The synopsis is pretty good, but it left out what I thought was the key point of the book (at least for me) which was that people already form attachments with cars, tomoguchi toys, cell phones, and other inanimate objects and that that capacity will easily transfer to robots. -Kelly On Mon, Sep 9, 2024 at 2:22?PM BillK via extropy-chat wrote: > > On Mon, 9 Sept 2024 at 06:24, Kelly Anderson via extropy-chat wrote: > > > > I still think the book: > > Love and Sex with Robots: The Evolution of Human-Robot Relationships > > by David Levy published in 2008 > > is one of the better treatments of this subject matter. Amazingly, the > > book is mostly about the human psychological predisposition to fall in > > love with cars, tomoguchi, and other inanimate objects. > > > > -Kelly > > _______________________________________________ > > > I asked for an AI summary of this book. > For a book written in 2008, it sounds years ahead of its time! > BillK > > The book "Love and Sex with Robots: The Evolution of Human-Robot Relationships" explores the emerging field of human-robot relationships, examining the potential for robots to become intimate partners and the implications of such relationships on human society. Written by David Levy, a renowned expert in artificial intelligence and robotics, the book provides a comprehensive overview of the current state of robotics and its potential future developments. > > The author argues that as robots become increasingly advanced and human-like, it is inevitable that humans will form emotional bonds with them. He predicts that by the 2040s, robots will be capable of simulating human-like conversation, leading to the development of romantic relationships between humans and robots. Levy also explores the potential benefits of such relationships, including the ability of robots to provide companionship to the elderly and those with disabilities. > > One of the key takeaways from the book is the distinction between androids and gynoids. Androids are male robots, while gynoids are female robots. Levy argues that gynoids will be more appealing to humans due to their perceived femininity and nurturing qualities. He also predicts that gynoids will be more likely to be used as sex robots, leading to a new form of prostitution. > > The book also examines the potential legal and ethical implications of human-robot relationships. Levy argues that as robots become more advanced, they will require rights and protections similar to those afforded to humans. He also predicts that the development of sex robots will lead to a re-evaluation of prostitution laws and the concept of consent. > > Some of the key lessons and practical applications from the book include: > > Robotics will revolutionize the sex industry: Levy predicts that sex robots will become increasingly popular, leading to a shift away from human prostitution. > Robots will provide companionship to the elderly and those with disabilities: As robots become more advanced, they will be able to provide emotional support and companionship to those in need. > Human-robot relationships will challenge traditional notions of love and intimacy: As humans form emotional bonds with robots, it will force a re-evaluation of what it means to love and be intimate with another being. > The development of robots will require a re-evaluation of ethics and laws: As robots become more advanced, they will require rights and protections similar to those afforded to humans, leading to a re-evaluation of ethics and laws. > > In conclusion, "Love and Sex with Robots" provides a comprehensive overview of the emerging field of human-robot relationships. The book's key takeaways highlight the potential benefits and implications of such relationships, including the potential for robots to provide companionship and the need for a re-evaluation of ethics and laws. As robotics continues to advance, this book provides a timely and thought-provoking exploration of the future of human-robot relationships. > > ------------------------------- > > > _______________________________________________ > extropy-chat mailing list > extropy-chat at lists.extropy.org > http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat From pharos at gmail.com Wed Sep 11 15:30:42 2024 From: pharos at gmail.com (BillK) Date: Wed, 11 Sep 2024 16:30:42 +0100 Subject: [ExI] Genetic Evidence Overrules Ecocide Theory of Easter Island Message-ID: Genetic Evidence Overrules Ecocide Theory of Easter Island Once And For All 12 September 2024 By Carly Cassella Quotes: The true story of Rapa Nui (named Easter Island by colonial Europeans) is not one of self-inflicted population collapse, the new findings suggest, but of cultural resilience. Genetic analysis indicates that Rapanui's civilization was actually growing until the 1860s, when Peruvian slave raids and subsequent epidemics brought by European colonial activity decimated the island's population to around 110 individuals. A large body of archaeological and anthropological data has already contradicted the ecocide theory of Rapa Nui. But this new research is the first to undermine the story using ancient genomic data. ----------------- The study was published in Nature. --------------------- They are saying that this proves that the famous story written by Jared Diamond in his best-selling book Collapse (2005) never actually happened. Maybe humans have the sense not to commit national suicide after all. BillK From danust2012 at gmail.com Wed Sep 11 17:21:35 2024 From: danust2012 at gmail.com (Dan TheBookMan) Date: Wed, 11 Sep 2024 10:21:35 -0700 Subject: [ExI] Genetic Evidence Overrules Ecocide Theory of Easter Island In-Reply-To: References: Message-ID: <0ADE2F3A-2029-4AEC-8DFA-C948EAF77CC3@gmail.com> On Sep 11, 2024, at 8:33?AM, BillK via extropy-chat wrote: > ?Genetic Evidence Overrules Ecocide Theory of Easter Island Once And For All > 12 September 2024 By Carly Cassella > > > Quotes: > The true story of Rapa Nui (named Easter Island by colonial Europeans) > is not one of self-inflicted population collapse, the new findings > suggest, but of cultural resilience. > > Genetic analysis indicates that Rapanui's civilization was actually > growing until the 1860s, when Peruvian slave raids and subsequent > epidemics brought by European colonial activity decimated the island's > population to around 110 individuals. > > A large body of archaeological and anthropological data has already > contradicted the ecocide theory of Rapa Nui. But this new research is > the first to undermine the story using ancient genomic data. > ----------------- > The study was published in Nature. > > --------------------- > > They are saying that this proves that the famous story written by > Jared Diamond in his best-selling book Collapse (2005) never actually > happened. > Maybe humans have the sense not to commit national suicide after all. > > BillK It seemed to me that almost as soon as Diamond?s book came out, researchers in the field disagreed. Sadly, the book was so popular that debunking its thesis on Rapa Nui will likely have to be done time and again. Regards, Dan From hkeithhenson at gmail.com Wed Sep 11 19:25:18 2024 From: hkeithhenson at gmail.com (Keith Henson) Date: Wed, 11 Sep 2024 12:25:18 -0700 Subject: [ExI] Genetic Evidence Overrules Ecocide Theory of Easter Island In-Reply-To: <0ADE2F3A-2029-4AEC-8DFA-C948EAF77CC3@gmail.com> References: <0ADE2F3A-2029-4AEC-8DFA-C948EAF77CC3@gmail.com> Message-ID: The problem with "debunking" is that the story just makes sense. It's no problem at all to generate a math model that fits the observed facts, such as the destruction of trees, the known facts like the abrupt end of making the statues, and the relatively small population the Europeans encountered. But what do I know? Keith On Wed, Sep 11, 2024 at 10:22?AM Dan TheBookMan via extropy-chat wrote: > > On Sep 11, 2024, at 8:33?AM, BillK via extropy-chat wrote: > > ?Genetic Evidence Overrules Ecocide Theory of Easter Island Once And For All > > 12 September 2024 By Carly Cassella > > > > > > Quotes: > > The true story of Rapa Nui (named Easter Island by colonial Europeans) > > is not one of self-inflicted population collapse, the new findings > > suggest, but of cultural resilience. > > > > Genetic analysis indicates that Rapanui's civilization was actually > > growing until the 1860s, when Peruvian slave raids and subsequent > > epidemics brought by European colonial activity decimated the island's > > population to around 110 individuals. > > > > A large body of archaeological and anthropological data has already > > contradicted the ecocide theory of Rapa Nui. But this new research is > > the first to undermine the story using ancient genomic data. > > ----------------- > > The study was published in Nature. > > > > --------------------- > > > > They are saying that this proves that the famous story written by > > Jared Diamond in his best-selling book Collapse (2005) never actually > > happened. > > Maybe humans have the sense not to commit national suicide after all. > > > > BillK > > It seemed to me that almost as soon as Diamond?s book came out, researchers in the field disagreed. Sadly, the book was so popular that debunking its thesis on Rapa Nui will likely have to be done time and again. > > Regards, > > Dan > _______________________________________________ > extropy-chat mailing list > extropy-chat at lists.extropy.org > http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat From danust2012 at gmail.com Wed Sep 11 22:40:22 2024 From: danust2012 at gmail.com (Dan TheBookMan) Date: Wed, 11 Sep 2024 15:40:22 -0700 Subject: [ExI] Genetic Evidence Overrules Ecocide Theory of Easter Island In-Reply-To: References: Message-ID: On Sep 11, 2024, at 12:25?PM, Keith Henson wrote: > ?The problem with "debunking" is that the story just makes sense. It's > no problem at all to generate a math model that fits the observed > facts, such as the destruction of trees, the known facts like the > abrupt end of making the statues, and the relatively small population > the Europeans encountered. > > But what do I know? > > Keith Well, how do you know there was a huge population there to begin with? I recall someone (you?) here stating there were 20,000 people on the island. But estimates based on archaeological data seem to place the highest population level well under 10,000 and probably something like 4,000 at its height. There?s also no evidence of a collapse through violence ? much less a collapse through ecological catastrophe. Yes, the rats probably ate up young trees and the islanders were trapped them and then wiped out local ground birds, but they adapted. It appears the Rapa Nuians were steadily growing in population until Europeans showed up and started raising for slaves and spreading diseases that the islanders had little resistance to. So what data do you have to support your view? Regards, Dan From hkeithhenson at gmail.com Thu Sep 12 04:00:50 2024 From: hkeithhenson at gmail.com (Keith Henson) Date: Wed, 11 Sep 2024 21:00:50 -0700 Subject: [ExI] Genetic Evidence Overrules Ecocide Theory of Easter Island In-Reply-To: References: Message-ID: Now, please understand that I have no first-hand knowledge, so what I know if from Google searches, like https://www.sciencealert.com ? scientists-closer-to-understanding-what-wiped-out-easter-island-society "Scientists Are Closer to Understanding What Wiped Out Easter Island ... "The Polynesian culture, called Rapa Nui, settled the island around 1200 AD, and the population is estimated to have been around 15,000 at its peak. But by the time Europeans settled the island in 1722, the population had declined to a couple of thousand, and by the 1860s, the entire culture was nearly entirely wiped out, with just over 100 individuals remaining." "By the time of European arrival in 1722, the island's population had dropped to 2,000?3,000 from a high of approximately 15,000 just a century earlier."[34] (Wikipedia) Does this make sense? The founding stock (from somewhere) is guessed to be 20 people. At a generation time of 4 per century, by 1600 they would be expected to grow 2^16 based on doubling every generation. It only takes 10 doublings to reach 20,000. Another way is to estimate agricultural productivity. The whole island is 164 square km. That is around 16,000 hectare. Much of the island was used to grow sweet potatoes and is "mulched" to this day with rocks. "sweet potatoes are the most efficient staple food to grow in terms of farmland, yielding approximately 70,000 kcal per hectare (28,000/acre) / day.[84]" A human is about 100 W, on a per day basis, about 2160 kcal. So a hectare would feed (eating nothing but sweet potatoes) 32 people. 16,000 people would take 500 hectares, around 1/32th the area of the island. Not proof, of course, but the numbers are not out of line. If you are going to argue for a much smaller number, then you need to suggest something that kept the population down. Keith On Wed, Sep 11, 2024 at 3:41?PM Dan TheBookMan via extropy-chat wrote: > > On Sep 11, 2024, at 12:25?PM, Keith Henson wrote: > > ?The problem with "debunking" is that the story just makes sense. It's > > no problem at all to generate a math model that fits the observed > > facts, such as the destruction of trees, the known facts like the > > abrupt end of making the statues, and the relatively small population > > the Europeans encountered. > > > > But what do I know? > > > > Keith > > Well, how do you know there was a huge population there to begin with? I recall someone (you?) here stating there were 20,000 people on the island. But estimates based on archaeological data seem to place the highest population level well under 10,000 and probably something like 4,000 at its height. > > There?s also no evidence of a collapse through violence ? much less a collapse through ecological catastrophe. Yes, the rats probably ate up young trees and the islanders were trapped them and then wiped out local ground birds, but they adapted. It appears the Rapa Nuians were steadily growing in population until Europeans showed up and started raising for slaves and spreading diseases that the islanders had little resistance to. So what data do you have to support your view? > > Regards, > > Dan > _______________________________________________ > extropy-chat mailing list > extropy-chat at lists.extropy.org > http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat From giulio at gmail.com Thu Sep 12 04:53:30 2024 From: giulio at gmail.com (Giulio Prisco) Date: Thu, 12 Sep 2024 06:53:30 +0200 Subject: [ExI] My new book "Irrational mechanics" is published! Message-ID: My new book "Irrational mechanics" is published! I wish to thank all the people on this list who gave me good ideas and comments. Irrational mechanics: Narrative sketch of a futurist science & a new religion, by Giulio Prisco. https://www.turingchurch.com/p/irrational-mechanics-published From pharos at gmail.com Thu Sep 12 09:11:45 2024 From: pharos at gmail.com (BillK) Date: Thu, 12 Sep 2024 10:11:45 +0100 Subject: [ExI] Genetic Evidence Overrules Ecocide Theory of Easter Island In-Reply-To: References: Message-ID: On Thu, 12 Sept 2024 at 05:03, Keith Henson via extropy-chat wrote: > > Now, please understand that I have no first-hand knowledge, so what I > know if from Google searches, like > > https://www.sciencealert.com ? > scientists-closer-to-understanding-what-wiped-out-easter-island-society > > "Scientists Are Closer to Understanding What Wiped Out Easter Island ... > If you are going to argue for a much smaller number, then you need to > suggest something that kept the population down. > > Keith > _______________________________________________ That study is from 2015. There has been much more research done since then. Quote: What Really Happened on Easter Island? A Columbia study helps debunk an old theory about the island?s mysterious past. By Kevin Krajick '76GS, '77JRN Fall 2024 A new study by Columbia archaeologist Dylan Davis challenges this narrative, claiming that the Rapa Nui people did not overpopulate the island but rather maintained a small and stable settlement right up until the Europeans arrived. The evidence: a comprehensive survey of the island?s farmland that indicates that its inhabitants grew only enough crops to feed four thousand people at any given time. ?This shows that the population could never have been as big as some of the earlier estimates suggested,? says Davis, who is a postdoctoral research fellow at the Columbia Climate School. ---------------------- This is what the new DNA research published in 'Nature' has confirmed. BillK From hkeithhenson at gmail.com Fri Sep 13 04:26:49 2024 From: hkeithhenson at gmail.com (Keith Henson) Date: Thu, 12 Sep 2024 21:26:49 -0700 Subject: [ExI] Science this evening Message-ID: Artificial Arguments: Intense dialogues with AI chatbots reduce beliefs in conspiracies H. H. Thorp & B. Bago and J.-F. Bonnefon & T. H. Costello et al. That's something else. Keith From pharos at gmail.com Sun Sep 15 10:48:04 2024 From: pharos at gmail.com (BillK) Date: Sun, 15 Sep 2024 11:48:04 +0100 Subject: [ExI] Science this evening In-Reply-To: References: Message-ID: On Fri, 13 Sept 2024 at 05:29, Keith Henson via extropy-chat wrote: > > Artificial Arguments: Intense dialogues with AI chatbots reduce > beliefs in conspiracies > H. H. Thorp & B. Bago and J.-F. Bonnefon & T. H. Costello et al. > > That's something else. > Keith > _______________________________________________ This study seems to be all over the news channels now ? even in "Nature". Original study here ? Nature article here ? So, guess what? There is now a conspiracy theory starting about this study! Quote: Are New-World-Order Elites Plotting to Use AI to ?Deprogram? So-Called Conspiracy Theorists? 'This is really exciting. It seemed like it worked and it worked quite broadly...' Posted by Jacob Bruns September 13, 2024 Might the New World Order use biased, pre-manipulated artificial intelligence programs to try to ?deprogram? those with unpopular opinions by persuading them that their logic does not compute? Critics have already sounded the alarm that leftist radicals in Silicon Valley and elsewhere were manipulating the algorithms used to train AI so that it automatically defaulted to anti-conservative biases. The next step may be programming any verboten viewpoints into the realm of ?conspiracy theory,? then having powerful computers challenge human users to a battle of logic that inevitably is stacked against them with cherry-picked data. ----------------- You can't win. Everything you believe is probably a conspiracy theory! :) BillK From pharos at gmail.com Tue Sep 17 13:27:14 2024 From: pharos at gmail.com (BillK) Date: Tue, 17 Sep 2024 14:27:14 +0100 Subject: [ExI] =?utf-8?q?Why_OpenAI=E2=80=99s_new_model_is_such_a_big_dea?= =?utf-8?q?l?= Message-ID: Why OpenAI?s new model is such a big deal The bulk of LLM progress until now has been language-driven. This new model enters the realm of complex reasoning, with implications for physics, coding, and more. By James O'Donnell September 17, 2024 Quotes: Unlike previous models that are well suited for language tasks like writing and editing, OpenAI o1 is focused on multistep ?reasoning,? the type of process required for advanced mathematics, coding, or other STEM-based questions. It uses a ?chain of thought? technique, according to OpenAI. ?It learns to recognize and correct its mistakes. It learns to break down tricky steps into simpler ones. It learns to try a different approach when the current one isn?t working,? the company wrote in a blog post on its website. It?s a big deal because it brings ?chain-of-thought? reasoning in an AI model to a mass audience, says Matt Welsh, an AI researcher and founder of the LLM startup Fixie. ------------------- Looks like LLMs are changing into AIs that can do logical thinking. BillK From ben at zaiboc.net Tue Sep 17 17:58:04 2024 From: ben at zaiboc.net (Ben Zaiboc) Date: Tue, 17 Sep 2024 18:58:04 +0100 Subject: [ExI] ETs/Aliens In-Reply-To: References: Message-ID: On 17/09/2024 14:28, Keith Henson wrote: > " perhaps in an SF story," > > I did that a long time ago. Do you need me to post a pointer again? > > Best wishes, > > Keith The Clinic Seed was good, and it does mention slowing down someone's perception of time. I can recommend it to anyone who hasn't read it. While The Clinic Seed deals with the impact of uploading itself on human society, what I had in mind was afterwards (in a setting where the initial effects of uploading are over and it's a common or even universal thing), a more focused exploration of the societal implications of the ability of uploads to change how quickly time flows for them. Implications for both the uploaded and the un-uploaded (assuming there are any). How this ability might affect interpersonal relationships, people's psychology and how it could change the way society functions. How it may be, for some, not just an ability but a necessity, for various reasons (like sustaining a multi-tiered system with different units running at different clock-speeds, as per my previous post). Ben -------------- next part -------------- An HTML attachment was scrubbed... URL: From msd001 at gmail.com Tue Sep 17 22:26:23 2024 From: msd001 at gmail.com (Mike Dougherty) Date: Tue, 17 Sep 2024 18:26:23 -0400 Subject: [ExI] ETs/Aliens In-Reply-To: References: Message-ID: On Tue, Sep 17, 2024, 1:59 PM Ben Zaiboc via extropy-chat < extropy-chat at lists.extropy.org> wrote: > > While The Clinic Seed deals with the impact of uploading itself on human > society, what I had in mind was afterwards (in a setting where the initial > effects of uploading are over and it's a common or even universal thing), a > more focused exploration of the societal implications of the ability of > uploads to change how quickly time flows for them. Implications for both > the uploaded and the un-uploaded (assuming there are any). How this ability > might affect interpersonal relationships, people's psychology and how it > could change the way society functions. How it may be, for some, not just > an ability but a necessity, for various reasons (like sustaining a > multi-tiered system with different units running at different clock-speeds, > as per my previous post). > Have you read Greg Egan's "Permutation City"? Many ideas of uploaded 'being' are handled matter-of-factly in the course of the larger story. "Diaspora" goes even farther with a protagonist creation from semi-randomness, then escaping the confines of the successively weirder universes while discovering the rules of a metaverse > -------------- next part -------------- An HTML attachment was scrubbed... URL: From pharos at gmail.com Fri Sep 20 10:13:17 2024 From: pharos at gmail.com (BillK) Date: Fri, 20 Sep 2024 11:13:17 +0100 Subject: [ExI] Quantum Physics 'spookiness' still the best interpretation Message-ID: Hidden variable alternative to quantum spookiness fails Do we actually live in a deterministic Universe, despite quantum physics? An alternative, non-spooky interpretation has now been ruled out. Ethan Siegel September 19, 2024 Quotes: >From Newton through Maxwell, every particle and interaction known seemed to obey a deterministic set of equations, but the discovery of radioactivity and quantum physics quickly changed all that. In quantum physics, you can only predict the probability distribution of a set of possible outcomes, with an actual measurement required to tell you which outcome has actually occurred. One interpretation of quantum physics, Bohmian mechanics, involves hidden variables and seeks to do away with quantum spookiness entirely. Its one measurable prediction just failed. --------------------- Quantum physics remains really 'spooky', whether you like it or not! :) BillK From atymes at gmail.com Fri Sep 20 10:57:41 2024 From: atymes at gmail.com (Adrian Tymes) Date: Fri, 20 Sep 2024 06:57:41 -0400 Subject: [ExI] Quantum Physics 'spookiness' still the best interpretation In-Reply-To: References: Message-ID: As usual with articles written like this, the meat of the proof far underperformed what is claimed. One specific, simplified form of determinism was counterproven, not all forms of determinism. On Fri, Sep 20, 2024, 6:15?AM BillK via extropy-chat < extropy-chat at lists.extropy.org> wrote: > Hidden variable alternative to quantum spookiness fails > > Do we actually live in a deterministic Universe, despite quantum > physics? > An alternative, non-spooky interpretation has now been ruled out. > Ethan Siegel September 19, 2024 > > < > https://bigthink.com/starts-with-a-bang/hidden-variable-quantum-spookiness/ > > > Quotes: > From Newton through Maxwell, every particle and interaction known > seemed to obey a deterministic set of equations, but the discovery of > radioactivity and quantum physics quickly changed all that. > In quantum physics, you can only predict the probability distribution > of a set of possible outcomes, with an actual measurement required to > tell you which outcome has actually occurred. > One interpretation of quantum physics, Bohmian mechanics, involves > hidden variables and seeks to do away with quantum spookiness > entirely. Its one measurable prediction just failed. > --------------------- > > Quantum physics remains really 'spooky', whether you like it or not! :) > BillK > _______________________________________________ > extropy-chat mailing list > extropy-chat at lists.extropy.org > http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat > -------------- next part -------------- An HTML attachment was scrubbed... URL: From pharos at gmail.com Fri Sep 20 11:52:36 2024 From: pharos at gmail.com (BillK) Date: Fri, 20 Sep 2024 12:52:36 +0100 Subject: [ExI] Quantum Physics 'spookiness' still the best interpretation In-Reply-To: References: Message-ID: On Fri, 20 Sept 2024 at 11:57, Adrian Tymes wrote: > As usual with articles written like this, the meat of the proof far underperformed what is claimed. > One specific, simplified form of determinism was counterproven, not all forms of determinism. >----------------------------------------- The article agrees with you. But quantum spookiness is the best we have at present. BillK Quote: We may not have the ultimate, complete, full answer to the question of how the Universe works, but we have knocked down a tremendous number of pretenders from the throne. If your predictions disagree with experiments, your theory is wrong, no matter how popular, compelling, or beautiful it happens to be. We have not yet ruled out all possible incarnations of Bohmian mechanics, or of more general pilot wave theories, or of all possible quantum mechanics interpretations that possess hidden variables. In fact, it may not ever be possible to do so. However, every attempt to construct a theory that agrees with experiment requires some level of quantum spookiness that simply cannot be done away with. ---------------- From efc at disroot.org Fri Sep 20 12:10:02 2024 From: efc at disroot.org (efc at disroot.org) Date: Fri, 20 Sep 2024 14:10:02 +0200 (CEST) Subject: [ExI] Quantum Physics 'spookiness' still the best interpretation In-Reply-To: References: Message-ID: On Fri, 20 Sep 2024, BillK via extropy-chat wrote: > On Fri, 20 Sept 2024 at 11:57, Adrian Tymes wrote: >> As usual with articles written like this, the meat of the proof far underperformed what is claimed. >> One specific, simplified form of determinism was counterproven, not all forms of determinism. >> ----------------------------------------- > > The article agrees with you. > But quantum spookiness is the best we have at present. > BillK > > Quote: > We may not have the ultimate, complete, full answer to the question of > how the Universe works, but we have knocked down a tremendous number > of pretenders from the throne. If your predictions disagree with > experiments, your theory is wrong, no matter how popular, compelling, > or beautiful it happens to be. We have not yet ruled out all possible > incarnations of Bohmian mechanics, or of more general pilot wave > theories, or of all possible quantum mechanics interpretations that > possess hidden variables. In fact, it may not ever be possible to do > so. However, every attempt to construct a theory that agrees with > experiment requires some level of quantum spookiness that simply > cannot be done away with. I would have liked to see this, first thing, and not last. That would save a lot of time for a non-scientist like me. ;) From pharos at gmail.com Fri Sep 20 12:55:37 2024 From: pharos at gmail.com (BillK) Date: Fri, 20 Sep 2024 13:55:37 +0100 Subject: [ExI] Large Hadron Collider Breakthrough: Quantum Entanglement Like Never Before Message-ID: Large Hadron Collider Breakthrough: Quantum Entanglement Like Never Before By CERN September 20, 2024 Quote: Quantum entanglement, an intriguing aspect of quantum physics, allows particles to remain interconnected regardless of distance. This phenomenon was explored at new heights in 2023 when the ATLAS collaboration at the Large Hadron Collider observed entanglement between top quarks, marking a major advancement in understanding the universe?s fundamental forces. Quantum entanglement is a fascinating feature of quantum physics ? the theory of the very small. If two particles are quantum-entangled, the state of one particle is tied to that of the other, no matter how far apart the particles are. This mind-bending phenomenon, which has no analog in classical physics, has been observed in a wide variety of systems and has found several important applications, such as quantum cryptography and quantum computing. --------------------- 'Spooky action at a distance', confirmed for the heaviest known fundamental particles. Top quarks are each as heavy as an atom of gold and can only be produced at colliders, such as LHC. BillK From ben at zaiboc.net Sat Sep 21 09:02:46 2024 From: ben at zaiboc.net (Ben Zaiboc) Date: Sat, 21 Sep 2024 10:02:46 +0100 Subject: [ExI] ETs/Aliens In-Reply-To: References: Message-ID: <08c6cb36-03e1-4ed4-bd01-2b1f2a0d9076@zaiboc.net> On 17/09/2024, Mike Dougherty wrote: > On Tue, Sep 17, 2024, 1:59 PM Ben Zaiboc via extropy-chat wrote: __ While The Clinic Seed deals with the impact of uploading itself on human society, what I had in mind was afterwards (in a setting where the initial effects of uploading are over and it's a common or even universal thing), a more focused exploration of the societal implications of the ability of uploads to change how quickly time flows for them. Implications for both the uploaded and the un-uploaded (assuming there are any). How this ability might affect interpersonal relationships, people's psychology and how it could change the way society functions. How it may be, for some, not just an ability but a necessity, for various reasons (like sustaining a multi-tiered system with different units running at different clock-speeds, as per my previous post). > Have you read Greg Egan's "Permutation City"? > Many ideas of uploaded 'being' are handled matter-of-factly in the course of the larger story. > "Diaspora" goes even farther with a protagonist creation from semi-randomness, then escaping the confines of the successively weirder universes while discovering the rules of a metaverse Yes, I have. And Diaspora, and just about all of his stuff, I think. He's one of my favourite authors. I particularly liked the idea of people beaming themselves around the galaxy to different locations, sometimes a data-centre, remaining an upload, sometimes being instantiated into a physical body. And the fact that he doesn't try to get around the speed of light. So someone might take a few thousand objective years (and no time at all, subjectively) to go to their destination, leaving behind their friends and family, who they might not see again for hundreds of thousands of years, or even never (or might-as-well-be-never, given that people would be certain to change over that timespan, and might be unrecognisable even if you did meet them again). Just that would require a certain degree of psychological rewiring from how we are now. People living at different speeds would be - well, I'm not sure I can wrap my head around it, and I reckon I'm pretty imaginative. That's why I'd like to see someone tackle it in a story. Or a whole bunch of stories. (Just to complicate things more, what about people splitting off copies of themselves, that then run at different speeds! - Actually, Sean Williams touches on this, in his 'Astropolis' stories (of which I've only read the first book. A bit tricky to get hold of the rest)). Hm, I wonder if the Tabbians (If you can call them that (if they exist)) are beaming themselves around between those 24 or so stars (or probably more by now)?. And I wonder if any gamma-ray spillover might come our way, and be detectable? And one day, perhaps even decodable? It would be funny if we learned how to encode minds into a form they can be transmitted, by studying alien transmissions! (more SF material there, perhaps :D ) I'd suggest keeping a good long-term record of any gamma-ray (or x-ray, or whatever) emissions from that direction. Just in case. Ben -------------- next part -------------- An HTML attachment was scrubbed... URL: From pharos at gmail.com Sat Sep 21 15:49:25 2024 From: pharos at gmail.com (BillK) Date: Sat, 21 Sep 2024 16:49:25 +0100 Subject: [ExI] Leading AI Scientists Warn AI Could Escape Control at Any Moment Message-ID: Leading AI Scientists Warn AI Could Escape Control at Any Moment "Loss of human control or malicious use of these AI systems could lead to catastrophic outcomes." Sep 21, 2024 byNoor Al-Sibai. Quotes: "Rapid advances in artificial intelligence systems? capabilities are pushing humanity closer to a world where AI meets and surpasses human intelligence," begins the statement from International Dialogues on AI Safety (IDAIS), a cross-cultural consortium of scientists intent on mitigating AI risks. "Experts agree these AI systems are likely to be developed in the coming decades, with many of them believing they will arrive imminently," the IDAIS statement continues. "Loss of human control or malicious use of these AI systems could lead to catastrophic outcomes for all of humanity." ------------------ Well, I suppose keeping control of AGI is a good idea in theory, but it faces a lot of opposition. Do they really think they can control something that greatly surpasses human intelligence? Other AI experts are saying that too much regulation will slow down development and let other countries leap ahead. So they are opposing restrictive regulations. Then there are the military uses of AI to consider. Weaponising AI is seen as an absolute necessity. Every nation wants to be the first to develop far superior weapons. To me, it looks like AGI is so powerful that every nation will decide to say, "Damn the torpedoes, full speed ahead!". BillK From atymes at gmail.com Sat Sep 21 15:55:35 2024 From: atymes at gmail.com (Adrian Tymes) Date: Sat, 21 Sep 2024 11:55:35 -0400 Subject: [ExI] Leading AI Scientists Warn AI Could Escape Control at Any Moment In-Reply-To: References: Message-ID: AI systems are already being used maliciously. There is no plausible means of utterly preventing this, but there are means of countering it. It would help if groups like this would get out of the way and let those means be developed. On Sat, Sep 21, 2024 at 11:51?AM BillK via extropy-chat < extropy-chat at lists.extropy.org> wrote: > Leading AI Scientists Warn AI Could Escape Control at Any Moment > "Loss of human control or malicious use of these AI systems could lead > to catastrophic outcomes." > Sep 21, 2024 byNoor Al-Sibai. > > > Quotes: > "Rapid advances in artificial intelligence systems? capabilities are > pushing humanity closer to a world where AI meets and surpasses human > intelligence," begins the statement from International Dialogues on AI > Safety (IDAIS), a cross-cultural consortium of scientists intent on > mitigating AI risks. > "Experts agree these AI systems are likely to be developed in the > coming decades, with many of them believing they will arrive > imminently," the IDAIS statement continues. "Loss of human control or > malicious use of these AI systems could lead to catastrophic outcomes > for all of humanity." > ------------------ > > Well, I suppose keeping control of AGI is a good idea in theory, but > it faces a lot of opposition. > Do they really think they can control something that greatly surpasses > human intelligence? > Other AI experts are saying that too much regulation will slow down > development and let other countries leap ahead. So they are opposing > restrictive regulations. > Then there are the military uses of AI to consider. Weaponising AI is > seen as an absolute necessity. Every nation wants to be the first to > develop far superior weapons. > > To me, it looks like AGI is so powerful that every nation will decide > to say, "Damn the torpedoes, full speed ahead!". > > BillK > > _______________________________________________ > extropy-chat mailing list > extropy-chat at lists.extropy.org > http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat > -------------- next part -------------- An HTML attachment was scrubbed... URL: From pharos at gmail.com Sat Sep 21 16:16:56 2024 From: pharos at gmail.com (BillK) Date: Sat, 21 Sep 2024 17:16:56 +0100 Subject: [ExI] AI reviving USA nuclear power industry Message-ID: Microsoft inks deal to restart Three Mile Island nuclear reactor to fuel its voracious AI ambitions By Anton Shilov, published 20 Sept 2024 Quote: A lot of power for AI and cloud datacenters. Modern AI data centers consume enormous amounts of power, and it looks like they will get even more power-hungry in the coming years as companies like Google, Microsoft, Meta, and OpenAI strive towards artificial general intelligence (AGI). Oracle has already outlined plans to use nuclear power plants for its 1-gigawatt datacenters. It looks like Microsoft plans to do the same as it just inked a deal to restart a nuclear power plant to feed its data centers, reports Bloomberg. Constellation Energy will invest $1.6 billion to restart its Three Mile Island nuclear plant in Pennsylvania. The revived reactor will provide clean electricity to Microsoft for 20 years, supporting the tech giant's AI and cloud computing energy needs. This reactor had a generating capacity of approximately 819 megawatts (MW) of electricity, which is enough power for a small to medium-sized city with hundreds of thousands of homes. The plant should be operational by 2028, and it will serve Microsoft exclusively. ----------------------- So, every AGI will be looking after its own nuclear power station. These AGIs wouldn't ever threaten to make their power stations go critical, if humans don't behave, would they? No, of course not. Stop worrying! BillK From atymes at gmail.com Sat Sep 21 16:29:35 2024 From: atymes at gmail.com (Adrian Tymes) Date: Sat, 21 Sep 2024 12:29:35 -0400 Subject: [ExI] AI reviving USA nuclear power industry In-Reply-To: References: Message-ID: When speaking of nuclear reactors, "critical" means "operating normally". "Going critical" would not ordinarily be a threat. But nuclear plants still require fuel. A wannabe rogue AI would be better served by one of those space-based data centers, coupled with a robotic lunar mining and manufacturing plant to replace worn-out solar panels and gradually expand the data center. On Sat, Sep 21, 2024 at 12:18?PM BillK via extropy-chat < extropy-chat at lists.extropy.org> wrote: > Microsoft inks deal to restart Three Mile Island nuclear reactor to > fuel its voracious AI ambitions > By Anton Shilov, published 20 Sept 2024 > > < > https://www.tomshardware.com/tech-industry/artificial-intelligence/microsoft-inks-deal-to-restart-three-mile-island-nuclear-reactor-to-fuel-its-voracious-ai-ambitions > > > Quote: > A lot of power for AI and cloud datacenters. > Modern AI data centers consume enormous amounts of power, and it looks > like they will get even more power-hungry in the coming years as > companies like Google, Microsoft, Meta, and OpenAI strive towards > artificial general intelligence (AGI). Oracle has already outlined > plans to use nuclear power plants for its 1-gigawatt datacenters. It > looks like Microsoft plans to do the same as it just inked a deal to > restart a nuclear power plant to feed its data centers, reports > Bloomberg. > Constellation Energy will invest $1.6 billion to restart its Three > Mile Island nuclear plant in Pennsylvania. The revived reactor will > provide clean electricity to Microsoft for 20 years, supporting the > tech giant's AI and cloud computing energy needs. This reactor had a > generating capacity of approximately 819 megawatts (MW) of > electricity, which is enough power for a small to medium-sized city > with hundreds of thousands of homes. The plant should be operational > by 2028, and it will serve Microsoft exclusively. > ----------------------- > > So, every AGI will be looking after its own nuclear power station. > These AGIs wouldn't ever threaten to make their power stations go > critical, if humans don't behave, would they? > No, of course not. Stop worrying! > > BillK > _______________________________________________ > extropy-chat mailing list > extropy-chat at lists.extropy.org > http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat > -------------- next part -------------- An HTML attachment was scrubbed... URL: From hkeithhenson at gmail.com Sat Sep 21 16:55:12 2024 From: hkeithhenson at gmail.com (Keith Henson) Date: Sat, 21 Sep 2024 09:55:12 -0700 Subject: [ExI] AI reviving USA nuclear power industry In-Reply-To: References: Message-ID: Correct on what going critical means in nuclear reactors. "wannabe rogue AI" An AI doesn't want anything unless humans program it into the AI. There are times when anthropomorphizing leads us astray. Keith On Sat, Sep 21, 2024 at 9:31?AM Adrian Tymes via extropy-chat wrote: > > When speaking of nuclear reactors, "critical" means "operating normally". "Going critical" would not ordinarily be a threat. > > But nuclear plants still require fuel. A wannabe rogue AI would be better served by one of those space-based data centers, coupled with a robotic lunar mining and manufacturing plant to replace worn-out solar panels and gradually expand the data center. > > On Sat, Sep 21, 2024 at 12:18?PM BillK via extropy-chat wrote: >> >> Microsoft inks deal to restart Three Mile Island nuclear reactor to >> fuel its voracious AI ambitions >> By Anton Shilov, published 20 Sept 2024 >> >> >> Quote: >> A lot of power for AI and cloud datacenters. >> Modern AI data centers consume enormous amounts of power, and it looks >> like they will get even more power-hungry in the coming years as >> companies like Google, Microsoft, Meta, and OpenAI strive towards >> artificial general intelligence (AGI). Oracle has already outlined >> plans to use nuclear power plants for its 1-gigawatt datacenters. It >> looks like Microsoft plans to do the same as it just inked a deal to >> restart a nuclear power plant to feed its data centers, reports >> Bloomberg. >> Constellation Energy will invest $1.6 billion to restart its Three >> Mile Island nuclear plant in Pennsylvania. The revived reactor will >> provide clean electricity to Microsoft for 20 years, supporting the >> tech giant's AI and cloud computing energy needs. This reactor had a >> generating capacity of approximately 819 megawatts (MW) of >> electricity, which is enough power for a small to medium-sized city >> with hundreds of thousands of homes. The plant should be operational >> by 2028, and it will serve Microsoft exclusively. >> ----------------------- >> >> So, every AGI will be looking after its own nuclear power station. >> These AGIs wouldn't ever threaten to make their power stations go >> critical, if humans don't behave, would they? >> No, of course not. Stop worrying! >> >> BillK >> _______________________________________________ >> extropy-chat mailing list >> extropy-chat at lists.extropy.org >> http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat > > _______________________________________________ > extropy-chat mailing list > extropy-chat at lists.extropy.org > http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat From pharos at gmail.com Sat Sep 21 19:18:46 2024 From: pharos at gmail.com (BillK) Date: Sat, 21 Sep 2024 20:18:46 +0100 Subject: [ExI] Long-lived 'blue zones' debunked Message-ID: Research finds that most of the claims about people living over 105 are wrong. Saul Justin Newman Published: September 13, 2024 Quotes: ?The data on extreme human ageing is rotten from the inside out? Okinawa in Japan is one of these zones. There was a Japanese government review in 2010, which found that 82% of the people aged over 100 in Japan turned out to be dead. The secret to living to 110 was, don?t register your death. According to the Greek minister that hands out the pensions, over 9,000 people over the age of 100 are dead and collecting a pension at the same time. In Italy, some 30,000 ?living? pension recipients were found to be dead in 1997. Regions where people most often reach 100-110 years old are the ones where there?s the most pressure to commit pension fraud, and they also have the worst records. ------------------------ That means the famous 'blue zones' don't have the secret to long-life. We have to take their advice on diet and life-style with a large pinch of salt. (Careful though ? too much salt is bad for you). :) BillK From pharos at gmail.com Sat Sep 21 22:03:40 2024 From: pharos at gmail.com (BillK) Date: Sat, 21 Sep 2024 23:03:40 +0100 Subject: [ExI] AI reviving USA nuclear power industry In-Reply-To: References: Message-ID: On Sat, 21 Sept 2024 at 17:57, Keith Henson via extropy-chat wrote: > An AI doesn't want anything unless humans program it into the AI. > There are times when anthropomorphizing leads us astray. > Keith > _______________________________________________ That is correct for the present early-stage AIs. But AIs won't stay like that for very long. That's why these leading AI scientists are panicking about keeping control of AGIs. The whole alignment problem discussion is about how to keep AGI from misbehaving. When an AGI becomes superior to human intelligence, then the boot is on the other foot. Then the AGI will be worrying about how to keep humans from misbehaving. BillK From hkeithhenson at gmail.com Sat Sep 21 22:47:28 2024 From: hkeithhenson at gmail.com (Keith Henson) Date: Sat, 21 Sep 2024 15:47:28 -0700 Subject: [ExI] AI reviving USA nuclear power industry In-Reply-To: References: Message-ID: Sounds like a good idea to me. Maybe the AIs can do better than humans. It's not a high bar. Keith On Sat, Sep 21, 2024 at 3:05?PM BillK via extropy-chat wrote: > > On Sat, 21 Sept 2024 at 17:57, Keith Henson via extropy-chat > wrote: > > An AI doesn't want anything unless humans program it into the AI. > > There are times when anthropomorphizing leads us astray. > > Keith > > _______________________________________________ > > > That is correct for the present early-stage AIs. > But AIs won't stay like that for very long. > > That's why these leading AI scientists are panicking about keeping > control of AGIs. The whole alignment problem discussion is about how > to keep AGI from misbehaving. When an AGI becomes superior to human > intelligence, then the boot is on the other foot. > Then the AGI will be worrying about how to keep humans from misbehaving. > > BillK > _______________________________________________ > extropy-chat mailing list > extropy-chat at lists.extropy.org > http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat From pharos at gmail.com Wed Sep 25 22:29:37 2024 From: pharos at gmail.com (BillK) Date: Wed, 25 Sep 2024 23:29:37 +0100 Subject: [ExI] =?utf-8?q?America=E2=80=99s_Cup_2024_yachts_are_amazing_ma?= =?utf-8?q?chines?= Message-ID: America?s Cup boats: 8 facts about the AC75 and why they?re unique Toby Heppell August 20, 2024 Quotes: The AC75 is the class of boat that takes part in the America?s Cup and are arguably the most radical boats the competition has ever seen. There are plenty who argue that this technology is so far beyond the bounds of what most people consider sailing as to be an entirely different sport. But one thing is certain: the current America?s Cup boats, the AC75s, are unlike anything seen before and are showcasing to the world just what is possible under sail power alone. 1 Unimaginable speed 2 A storm onboard the AC75 3 Righting moment changes 4 ?Cyclors? return to power America?s Cup boats 5 America?s Cup boats may not be heading where they point 6 The foils are heavy. Very heavy. 7 Sails can invert at the head 8 America?s Cup meets F1 ------------ These machines cost millions of dollars to build. Once you add in all the other expenses, you are talking about hundreds of millions of dollars. BillK From pharos at gmail.com Fri Sep 27 16:35:06 2024 From: pharos at gmail.com (BillK) Date: Fri, 27 Sep 2024 17:35:06 +0100 Subject: [ExI] In future, will everybody wear their own body cam? Message-ID: Surveillance cameras are everywhere nowadays in cities, cars, homes, phones, etc. Police and many workers also wear body cameras. They are popular for increased safety, crime evidence, theft reduction, and yes, surveillance, to keep people behaving responsibly. When AI spectacles become available in the next few years, they will likely have a camera recording feature. It will not be the government watching what everyone is doing. It will be everyone watching each other, in a constant state of surveillance. So, will everybody soon be wearing their own AI-assisted body-cam devices? BillK From atymes at gmail.com Fri Sep 27 16:45:17 2024 From: atymes at gmail.com (Adrian Tymes) Date: Fri, 27 Sep 2024 12:45:17 -0400 Subject: [ExI] In future, will everybody wear their own body cam? In-Reply-To: References: Message-ID: Might it be a near-term prospect that, in certain neighborhoods, it becomes "fashionable" for residents - especially the wealthy and/or well-connected - to routinely wear unobtrusive body cams in styles known to the police, as a "if you try to violate my rights, you know you're on camera" deal, and that is given as an unofficial but increasingly widely known excuse why only the poor and disconnected get roughed up? On Fri, Sep 27, 2024 at 12:37?PM BillK via extropy-chat < extropy-chat at lists.extropy.org> wrote: > Surveillance cameras are everywhere nowadays in cities, cars, homes, > phones, etc. Police and many workers also wear body cameras. They are > popular for increased safety, crime evidence, theft reduction, and > yes, surveillance, to keep people behaving responsibly. > > When AI spectacles become available in the next few years, they will > likely have a camera recording feature. > > It will not be the government watching what everyone is doing. It will > be everyone watching each other, in a constant state of surveillance. > > So, will everybody soon be wearing their own AI-assisted body-cam devices? > > BillK > _______________________________________________ > extropy-chat mailing list > extropy-chat at lists.extropy.org > http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat > -------------- next part -------------- An HTML attachment was scrubbed... URL: From efc at disroot.org Fri Sep 27 19:34:41 2024 From: efc at disroot.org (efc at disroot.org) Date: Fri, 27 Sep 2024 21:34:41 +0200 (CEST) Subject: [ExI] In future, will everybody wear their own body cam? In-Reply-To: References: Message-ID: <5e85133c-4652-5188-73cc-e0d12506d6e1@disroot.org> On Fri, 27 Sep 2024, BillK via extropy-chat wrote: > Surveillance cameras are everywhere nowadays in cities, cars, homes, > phones, etc. Police and many workers also wear body cameras. They are > popular for increased safety, crime evidence, theft reduction, and > yes, surveillance, to keep people behaving responsibly. > > When AI spectacles become available in the next few years, they will > likely have a camera recording feature. > > It will not be the government watching what everyone is doing. It will > be everyone watching each other, in a constant state of surveillance. > > So, will everybody soon be wearing their own AI-assisted body-cam devices? > > BillK > _______________________________________________ > extropy-chat mailing list > extropy-chat at lists.extropy.org > http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat > I think we are partly already there. Everyone has a smartphone, and if something happens out of the ordinary in town, you see plenty of people filming it already. So I think it is a fun exercise to extrapolate from where we are today, to, as you say, the time when everyone is wearing contacts with built in camera, or some other iny camera hidden on your person filming and storing everything on your home server or your phone. I heard that in the US, some insurance companies offer lower premiums if you have a camera in your car, and recently in sweden there was a case of the police using photos from a parked Tesla in a legal case. >From a personal point of view... I ask myself, what would make me bother? Privately I dislike photos, videos, and I seldom walk around in town with my phone on me. In business, everything important is done through email or contracts, so everything is recorded that way. Since I am a privacy nut, I would not take the insurance company up on the offer. So dear smartphone fans, what use would you have for 24x7 filming? From pharos at gmail.com Fri Sep 27 20:34:03 2024 From: pharos at gmail.com (BillK) Date: Fri, 27 Sep 2024 21:34:03 +0100 Subject: [ExI] In future, will everybody wear their own body cam? In-Reply-To: <5e85133c-4652-5188-73cc-e0d12506d6e1@disroot.org> References: <5e85133c-4652-5188-73cc-e0d12506d6e1@disroot.org> Message-ID: On Fri, 27 Sept 2024 at 20:37, efc--- via extropy-chat wrote: > > I think we are partly already there. Everyone has a smartphone, and if > something happens out of the ordinary in town, you see plenty of people > filming it already. > > So I think it is a fun exercise to extrapolate from where we are today, > to, as you say, the time when everyone is wearing contacts with built in > camera, or some other iny camera hidden on your person filming and storing > everything on your home server or your phone. > > I heard that in the US, some insurance companies offer lower premiums if > you have a camera in your car, and recently in sweden there was a case of > the police using photos from a parked Tesla in a legal case. > > From a personal point of view... I ask myself, what would make me bother? > Privately I dislike photos, videos, and I seldom walk around in town with > my phone on me. > > In business, everything important is done through email or contracts, so > everything is recorded that way. > > Since I am a privacy nut, I would not take the insurance company up on the > offer. > > So dear smartphone fans, what use would you have for 24x7 filming? > _______________________________________________ As Adrian mentioned, it could be useful for protection. As a deterrent to anyone approaching you to snatch your Rolex watch. It would also be evidence if any incident happens, to avoid the 'he said - she said' disputes. The video would be a support for your side in car accidents and is why insurance companies like them. (It also makes you a more careful driver, as you want the camera to support your version of the incident). I also see it as a general deterrent to misbehaviour. Anyone could be recorded at any time by anyone nearby. Just think how behaviour will change when anything you say or do could be displayed on the internet for the world to be offended by and make you into a non-person. Total surveillance should make humanity much better behaved. BillK From avant at sollegro.com Sat Sep 28 15:15:36 2024 From: avant at sollegro.com (Stuart LaForge) Date: Sat, 28 Sep 2024 08:15:36 -0700 Subject: [ExI] China building a Thorium molten salt reactor Message-ID: <069c2999256d575cf35b98246a9ff987@sollegro.com> China will start building a Thorium-based molten salt reactor in 2025. It is expected to start generating power in 2029-2030. https://www.neimagazine.com/news/china-to-build-worlds-first-thorium-molten-salt-npp-in-gobi-desert/?cf-view China has announced the construction of a nuclear power plant that will be fuelled by liquid fuel based on molten thorium salt. The Shanghai Institute of Applied Physics (SINAP) has been engaged in research in this area since 2011 focusing on liquid fluoride-thorium reactors (LFTRs). The construction of a prototype of a thorium molten salt reactor (TMSR) with a capacity of 2 MW began in September 2018 and was reportedly completed in August 2021. China is seeking to get full intellectual property rights to this technology. Now China plans to build the world?s first NPP based on molten salt in the Gobi desert. Construction will begin in 2025 with the aim of developing safer and more environmentally friendly nuclear energy. The reactor does not need water for cooling, since it uses liquid salt and carbon dioxide to transfer heat and generate electricity. In 2022, SINAP received permission from the Ministry of Ecology and Environmental Protection to commission an experimental MTSR. This is the first nuclear molten salt reactor since the United States stopped its molten salt test reactor in 1969. The application for the operation of the experimental reactor was considered in China in June 2023, it was considered to be fully compliant with safety requirements. The reactor will use fuel enriched in less than 20% U-235, with a thorium reserve of about 50 kg and a conversion factor of about 0.1. FLiBe ? a eutectic mixture of lithium fluoride and beryllium fluoride containing 99.95% lithium-7 will be used, and the fuel will consist of uranium tetrafluoride (UF4). It is expected that the implementation of the project will begin with some refuelling online and removal of gaseous fission products. However, after 5-8 years, all fuel salts will be disposed of for processing and separation of fission products and secondary actinides for storage. The reactor will launch an ongoing process of processing uranium and thorium salts with the operational separation of fission products and secondary actinoids. If this project is successful, China plans to fully commission a 373 MW reactor by 2030. ------------------------------------------ I hope that this is a wake up call to the West. NIMBYs be damned; if we don't get started on something similar, then China will be eating our lunch by the end of the next decade. Burning coal to power our Tesla EVs is not a viable alternative. Stuart LaForge From pharos at gmail.com Sat Sep 28 20:15:19 2024 From: pharos at gmail.com (BillK) Date: Sat, 28 Sep 2024 21:15:19 +0100 Subject: [ExI] Sam Altman - The Intelligence Age Message-ID: The Intelligence Age September 23, 2024 Quotes: In the next couple of decades, we will be able to do things that would have seemed like magic to our grandparents. It won?t happen all at once, but we?ll soon be able to work with AI that helps us accomplish much more than we ever could without AI; eventually we can each have a personal AI team, full of virtual experts in different areas, working together to create almost anything we can imagine. Our children will have virtual tutors who can provide personalized instruction in any subject, in any language, and at whatever pace they need. We can imagine similar ideas for better healthcare, the ability to create any kind of software someone can imagine, and much more. ------------------ He doesn't mention the Singularity, but he is very optimistic about the future benefits of AI, ? and soon! BillK From pharos at gmail.com Sun Sep 29 13:33:55 2024 From: pharos at gmail.com (BillK) Date: Sun, 29 Sep 2024 14:33:55 +0100 Subject: [ExI] AI moves away from thinking like humans Message-ID: AI begins its ominous split away from human thinking By Loz Blain September 29, 2024 Quotes: Freed from the crude human musings of Newton, and Einstein, and Hawking, embodied AIs will take a bizarre AlphaGo-style approach to understanding the world. They'll poke and prod at reality, and observe the results, and build up their own theories in their own languages about what works, what doesn't, and why. They won't approach reality like humans or animals do. They won't use a scientific method like ours, or split things into disciplines like physics and chemistry, or run the same kinds of experiments that helped humans master the materials and forces and energy sources around them and dominate the world. OpenAI's o1 model might not look like a quantum leap forward, sitting there in GPT's drab textual clothing, looking like just another invisible terminal typist. But it really is a step-change in the development of AI ? and a fleeting glimpse into exactly how these alien machines will eventually overtake humans in every conceivable way. ----------------------- Sings ? "This Could Be the Start of Something Big"......... BillK From atymes at gmail.com Sun Sep 29 14:11:01 2024 From: atymes at gmail.com (Adrian Tymes) Date: Sun, 29 Sep 2024 10:11:01 -0400 Subject: [ExI] AI moves away from thinking like humans In-Reply-To: References: Message-ID: I'm calling foul on that article title. "Moves away" says that this is definitely currently happening right now. The article text only speaks about what might possibly happen in the future, with no evidence cited of it happening right now. For example: sure, they won't run the exact same experiments, because those experiments have already been run and the AIs can learn from the results. But the same "kinds"? One could semantically argue "the same kinds of experiments that helped humans master the materials and forces of energy sources around them" into effectively being "literally only those experiments that were run before AIs", which is a useless type of "kind" for the point trying to be made. On Sun, Sep 29, 2024 at 9:36?AM BillK via extropy-chat < extropy-chat at lists.extropy.org> wrote: > AI begins its ominous split away from human thinking > By Loz Blain September 29, 2024 > > > Quotes: > Freed from the crude human musings of Newton, and Einstein, and > Hawking, embodied AIs will take a bizarre AlphaGo-style approach to > understanding the world. They'll poke and prod at reality, and observe > the results, and build up their own theories in their own languages > about what works, what doesn't, and why. > > They won't approach reality like humans or animals do. They won't use > a scientific method like ours, or split things into disciplines like > physics and chemistry, or run the same kinds of experiments that > helped humans master the materials and forces and energy sources > around them and dominate the world. > > OpenAI's o1 model might not look like a quantum leap forward, sitting > there in GPT's drab textual clothing, looking like just another > invisible terminal typist. But it really is a step-change in the > development of AI ? and a fleeting glimpse into exactly how these > alien machines will eventually overtake humans in every conceivable > way. > ----------------------- > > Sings ? "This Could Be the Start of Something Big"......... > > BillK > > _______________________________________________ > extropy-chat mailing list > extropy-chat at lists.extropy.org > http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat > -------------- next part -------------- An HTML attachment was scrubbed... URL: From steinberg.will at gmail.com Sun Sep 29 14:39:23 2024 From: steinberg.will at gmail.com (Will Steinberg) Date: Sun, 29 Sep 2024 10:39:23 -0400 Subject: [ExI] AI moves away from thinking like humans In-Reply-To: References: Message-ID: I just don?t think the article is saying much. Maybe AI will replace vapid navel-gazing thinkpieces like this. Nothing new here. On Sun, Sep 29, 2024 at 10:11?AM Adrian Tymes via extropy-chat < extropy-chat at lists.extropy.org> wrote: > I'm calling foul on that article title. > > "Moves away" says that this is definitely currently happening right now. > The article text only speaks about what might possibly happen in the > future, with no evidence cited of it happening right now. > > For example: sure, they won't run the exact same experiments, because > those experiments have already been run and the AIs can learn from the > results. But the same "kinds"? One could semantically argue "the same > kinds of experiments that helped humans master the materials and forces of > energy sources around them" into effectively being "literally only those > experiments that were run before AIs", which is a useless type of "kind" > for the point trying to be made. > > On Sun, Sep 29, 2024 at 9:36?AM BillK via extropy-chat < > extropy-chat at lists.extropy.org> wrote: > >> AI begins its ominous split away from human thinking >> By Loz Blain September 29, 2024 >> >> >> Quotes: >> Freed from the crude human musings of Newton, and Einstein, and >> Hawking, embodied AIs will take a bizarre AlphaGo-style approach to >> understanding the world. They'll poke and prod at reality, and observe >> the results, and build up their own theories in their own languages >> about what works, what doesn't, and why. >> >> They won't approach reality like humans or animals do. They won't use >> a scientific method like ours, or split things into disciplines like >> physics and chemistry, or run the same kinds of experiments that >> helped humans master the materials and forces and energy sources >> around them and dominate the world. >> >> OpenAI's o1 model might not look like a quantum leap forward, sitting >> there in GPT's drab textual clothing, looking like just another >> invisible terminal typist. But it really is a step-change in the >> development of AI ? and a fleeting glimpse into exactly how these >> alien machines will eventually overtake humans in every conceivable >> way. >> ----------------------- >> >> Sings ? "This Could Be the Start of Something Big"......... >> >> BillK >> >> _______________________________________________ >> extropy-chat mailing list >> extropy-chat at lists.extropy.org >> http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat >> > _______________________________________________ > extropy-chat mailing list > extropy-chat at lists.extropy.org > http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat > -------------- next part -------------- An HTML attachment was scrubbed... URL: From atymes at gmail.com Sun Sep 29 14:57:46 2024 From: atymes at gmail.com (Adrian Tymes) Date: Sun, 29 Sep 2024 10:57:46 -0400 Subject: [ExI] AI moves away from thinking like humans In-Reply-To: References: Message-ID: For all we know, an AI might have written this piece, or most of it. On Sun, Sep 29, 2024 at 10:41?AM Will Steinberg via extropy-chat < extropy-chat at lists.extropy.org> wrote: > I just don?t think the article is saying much. Maybe AI will replace > vapid navel-gazing thinkpieces like this. Nothing new here. > > On Sun, Sep 29, 2024 at 10:11?AM Adrian Tymes via extropy-chat < > extropy-chat at lists.extropy.org> wrote: > >> I'm calling foul on that article title. >> >> "Moves away" says that this is definitely currently happening right now. >> The article text only speaks about what might possibly happen in the >> future, with no evidence cited of it happening right now. >> >> For example: sure, they won't run the exact same experiments, because >> those experiments have already been run and the AIs can learn from the >> results. But the same "kinds"? One could semantically argue "the same >> kinds of experiments that helped humans master the materials and forces of >> energy sources around them" into effectively being "literally only those >> experiments that were run before AIs", which is a useless type of "kind" >> for the point trying to be made. >> >> On Sun, Sep 29, 2024 at 9:36?AM BillK via extropy-chat < >> extropy-chat at lists.extropy.org> wrote: >> >>> AI begins its ominous split away from human thinking >>> By Loz Blain September 29, 2024 >>> >>> >>> Quotes: >>> Freed from the crude human musings of Newton, and Einstein, and >>> Hawking, embodied AIs will take a bizarre AlphaGo-style approach to >>> understanding the world. They'll poke and prod at reality, and observe >>> the results, and build up their own theories in their own languages >>> about what works, what doesn't, and why. >>> >>> They won't approach reality like humans or animals do. They won't use >>> a scientific method like ours, or split things into disciplines like >>> physics and chemistry, or run the same kinds of experiments that >>> helped humans master the materials and forces and energy sources >>> around them and dominate the world. >>> >>> OpenAI's o1 model might not look like a quantum leap forward, sitting >>> there in GPT's drab textual clothing, looking like just another >>> invisible terminal typist. But it really is a step-change in the >>> development of AI ? and a fleeting glimpse into exactly how these >>> alien machines will eventually overtake humans in every conceivable >>> way. >>> ----------------------- >>> >>> Sings ? "This Could Be the Start of Something Big"......... >>> >>> BillK >>> >>> _______________________________________________ >>> extropy-chat mailing list >>> extropy-chat at lists.extropy.org >>> http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat >>> >> _______________________________________________ >> extropy-chat mailing list >> extropy-chat at lists.extropy.org >> http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat >> > _______________________________________________ > extropy-chat mailing list > extropy-chat at lists.extropy.org > http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat > -------------- next part -------------- An HTML attachment was scrubbed... URL: From pharos at gmail.com Sun Sep 29 15:53:45 2024 From: pharos at gmail.com (BillK) Date: Sun, 29 Sep 2024 16:53:45 +0100 Subject: [ExI] AI moves away from thinking like humans In-Reply-To: References: Message-ID: On Sun, 29 Sept 2024 at 16:00, Adrian Tymes via extropy-chat < extropy-chat at lists.extropy.org> wrote: > > For all we know, an AI might have written this piece, or most of it. > _______________________________________________ Oh, the article isn't trying to *prove* anything. It says in the article that it is speculation on what the future might hold. But if you want articles to quote evidence, then a search will find them. Even AI experts are getting over-excited by OpenAI o1. :) BillK Dr. Alan D. Thompson, a prominent AI researcher and analyst, provided a comprehensive breakdown of this groundbreaking development with *Financial Sense*. He is the author of the widely read AI newsletter, *The Memo* , which informs major laboratories, governments, and Fortune 500 companies worldwide. < https://www.financialsense.com/blog/21037/openais-o1-model-quantum-leap-ai-intelligence-insights-dr-alan-d-thompson > Quotes: OpenAI?s o1 Model: A Quantum Leap in AI Intelligence ? Insights from Dr Alan D. Thompson Sat, Sep 28, 2024 By Financial Sense OpenAI's newest AI model, o1, released on September 12, 2024, has shattered expectations and redefined the landscape of artificial intelligence. Its unprecedented performance on benchmark tests, surpassing PhD-level experts across nearly every domain, has sent ripples through the tech world and beyond. The advent of o1 has forced experts like Dr. Thompson to reassess their understanding of intelligence. He admits, "I need to re-evaluate my life's work. The performance of these models can't be overstated. They can't be overhyped." Perhaps most strikingly, o1's capabilities have surpassed our ability to test it. Dr. Thompson explains, "We're now at the stage it has to be designed by a peak human being... We don't actually have people smart enough to design test questions now that we have models like o1." Dr. Thompson posits that o1 represents a significant step toward Artificial General Intelligence (AGI)?a level of AI that can perform any intellectual task that a human being can. "With o1, we're in the proto-AGI phase,? he stated, acknowledging that while o1 has not yet achieved full AGI, it embodies many foundational aspects. The model?s ability to reason, adapt, and exhibit forms of self-awareness aligns closely with the characteristics expected of AGI. ------------------------ -------------- next part -------------- An HTML attachment was scrubbed... URL: From efc at disroot.org Sun Sep 29 19:59:37 2024 From: efc at disroot.org (efc at disroot.org) Date: Sun, 29 Sep 2024 21:59:37 +0200 (CEST) Subject: [ExI] In future, will everybody wear their own body cam? In-Reply-To: References: <5e85133c-4652-5188-73cc-e0d12506d6e1@disroot.org> Message-ID: <53a28605-eccc-300c-bc07-5f22917a41d5@disroot.org> On Fri, 27 Sep 2024, BillK via extropy-chat wrote: > On Fri, 27 Sept 2024 at 20:37, efc--- via extropy-chat > wrote: >> >> I think we are partly already there. Everyone has a smartphone, and if >> something happens out of the ordinary in town, you see plenty of people >> filming it already. >> >> So I think it is a fun exercise to extrapolate from where we are today, >> to, as you say, the time when everyone is wearing contacts with built in >> camera, or some other iny camera hidden on your person filming and storing >> everything on your home server or your phone. >> >> I heard that in the US, some insurance companies offer lower premiums if >> you have a camera in your car, and recently in sweden there was a case of >> the police using photos from a parked Tesla in a legal case. >> >> From a personal point of view... I ask myself, what would make me bother? >> Privately I dislike photos, videos, and I seldom walk around in town with >> my phone on me. >> >> In business, everything important is done through email or contracts, so >> everything is recorded that way. >> >> Since I am a privacy nut, I would not take the insurance company up on the >> offer. >> >> So dear smartphone fans, what use would you have for 24x7 filming? >> _______________________________________________ > > > As Adrian mentioned, it could be useful for protection. As a deterrent > to anyone approaching you to snatch your Rolex watch. It would also be Is this a common problem in the US? This is an honest question. I've had my run ins with mainly arabian robbers and assailants, but nothing serious ever happened and I managed to defend myself. _Despite_ probably having experienced way more violence than the average sweden, I would not even dream of walking around with a camera. It would not solve anything, and given the level of intelligence of the people involved in this incident, as well as laws against filming in public, I don't think it would work. So is this such a common scenario in the US and would it be effective? > evidence if any incident happens, to avoid the 'he said - she said' > disputes. The video would be a support for your side in car accidents > and is why insurance companies like them. > (It also makes you a more careful driver, as you want the camera to > support your version of the incident). Again, looking at the nr of incidents I've had, and how well it worked out without a camera, I don't see any real benefit. > I also see it as a general deterrent to misbehaviour. Anyone could be > recorded at any time by anyone nearby. > Just think how behaviour will change when anything you say or do could > be displayed on the internet for the world to be offended by and make you > into a non-person. > Total surveillance should make humanity much better behaved. Would you like to live your life with total surveillance and no privacy? I would definitely not, and would probably move out to a remote forest in case that became a reality. Also looking at the world, with the level of surveillance we have at our disposal today, it rather seems like the more surveillance and government control we have, the worse it gets. But horses for courses. ;) > > BillK > _______________________________________________ > extropy-chat mailing list > extropy-chat at lists.extropy.org > http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat > From efc at disroot.org Sun Sep 29 20:02:11 2024 From: efc at disroot.org (efc at disroot.org) Date: Sun, 29 Sep 2024 22:02:11 +0200 (CEST) Subject: [ExI] China building a Thorium molten salt reactor In-Reply-To: <069c2999256d575cf35b98246a9ff987@sollegro.com> References: <069c2999256d575cf35b98246a9ff987@sollegro.com> Message-ID: On Sat, 28 Sep 2024, Stuart LaForge via extropy-chat wrote: > China will start building a Thorium-based molten salt reactor in 2025. > It is expected to start generating power in 2029-2030. > > https://www.neimagazine.com/news/china-to-build-worlds-first-thorium-molten-salt-npp-in-gobi-desert/?cf-view > > > China has announced the construction of a nuclear power plant that will > be fuelled by liquid fuel based on molten thorium salt. The Shanghai > Institute of Applied Physics (SINAP) has been engaged in research in > this area since 2011 focusing on liquid fluoride-thorium reactors > (LFTRs). The construction of a prototype of a thorium molten salt > reactor (TMSR) with a capacity of 2 MW began in September 2018 and was > reportedly completed in August 2021. China is seeking to get full > intellectual property rights to this technology. > > Now China plans to build the world?s first NPP based on molten salt in > the Gobi desert. Construction will begin in 2025 with the aim of > developing safer and more environmentally friendly nuclear energy. The > reactor does not need water for cooling, since it uses liquid salt and > carbon dioxide to transfer heat and generate electricity. > > In 2022, SINAP received permission from the Ministry of Ecology and > Environmental Protection to commission an experimental MTSR. This is the > first nuclear molten salt reactor since the United States stopped its > molten salt test reactor in 1969. The application for the operation of > the experimental reactor was considered in China in June 2023, it was > considered to be fully compliant with safety requirements. > > The reactor will use fuel enriched in less than 20% U-235, with a > thorium reserve of about 50 kg and a conversion factor of about 0.1. > FLiBe ? a eutectic mixture of lithium fluoride and beryllium fluoride > containing 99.95% lithium-7 will be used, and the fuel will consist of > uranium tetrafluoride (UF4). > > It is expected that the implementation of the project will begin with > some refuelling online and removal of gaseous fission products. However, > after 5-8 years, all fuel salts will be disposed of for processing and > separation of fission products and secondary actinides for storage. The > reactor will launch an ongoing process of processing uranium and thorium > salts with the operational separation of fission products and secondary > actinoids. If this project is successful, China plans to fully > commission a 373 MW reactor by 2030. > > ------------------------------------------ > > I hope that this is a wake up call to the West. NIMBYs be damned; if we > don't get started on something similar, then China will be eating our > lunch by the end of the next decade. Burning coal to power our Tesla EVs > is not a viable alternative. > > Stuart LaForge > _______________________________________________ > extropy-chat mailing list > extropy-chat at lists.extropy.org > http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat > I agree completely. This is definitely the technology of the near-term future. I do hope the west would be able for once, to get sh*t done, and to deemphasize identity politics for the moment. ;) From atymes at gmail.com Sun Sep 29 20:21:31 2024 From: atymes at gmail.com (Adrian Tymes) Date: Sun, 29 Sep 2024 16:21:31 -0400 Subject: [ExI] In future, will everybody wear their own body cam? In-Reply-To: <53a28605-eccc-300c-bc07-5f22917a41d5@disroot.org> References: <5e85133c-4652-5188-73cc-e0d12506d6e1@disroot.org> <53a28605-eccc-300c-bc07-5f22917a41d5@disroot.org> Message-ID: On Sun, Sep 29, 2024 at 4:01?PM efc--- via extropy-chat < extropy-chat at lists.extropy.org> wrote: > On Fri, 27 Sep 2024, BillK via extropy-chat wrote: > > As Adrian mentioned, it could be useful for protection. As a deterrent > > to anyone approaching you to snatch your Rolex watch. It would also be > > Is this a common problem in the US? This is an honest question. I've had > my run ins with mainly arabian robbers and assailants, but nothing serious > ever happened and I managed to defend myself. _Despite_ probably having > experienced way more violence than the average sweden, I would not even > dream of walking around with a camera. It would not solve anything, and > given the level of intelligence of the people involved in this incident, > as well as laws against filming in public, I don't think it would work. > > So is this such a common scenario in the US and would it be effective? > It depends on where you are and who you are. The common robber would probably not be deterred. If they recognized a bodycam at all, they would probably think it was something more they could steal. The protection is against the police, who generally get training such that many can be expected to recognize a body cam - and that may be constantly broadcasting. Police, unlike robbers, are sometimes held accountable if sufficient public outcry is raised. There are only certain jurisdictions where such protection would be useful, and then only for certain classes of people - most famously, black people where the police force is thoroughly racist. In most locations, white people have no such problem if they look at least middle class. (Asian, Hispanic, et al are at various stages between.) -------------- next part -------------- An HTML attachment was scrubbed... URL: