<div dir="ltr"><div class="gmail_default" style="font-family:comic sans ms,sans-serif;font-size:large;color:#000000">Will we be like sheep when the level of accuracy of the ais reaches 99%? I think this would be a bad thing. bill w</div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Thu, Mar 7, 2024 at 5:09 AM BillK via extropy-chat <<a href="mailto:extropy-chat@lists.extropy.org" target="_blank">extropy-chat@lists.extropy.org</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div class="gmail_default" style="font-family:arial,sans-serif;font-size:small;color:rgb(0,0,0)"><h1>Can AI Solve Science?</h1>
March 5, 2024</div><div class="gmail_default" style="font-family:arial,sans-serif;font-size:small;color:rgb(0,0,0)"></div><div class="gmail_default" style="font-family:arial,sans-serif;font-size:small;color:rgb(0,0,0)"><<a href="https://writings.stephenwolfram.com/2024/03/can-ai-solve-science/" target="_blank">https://writings.stephenwolfram.com/2024/03/can-ai-solve-science/</a>></div><div class="gmail_default" style="font-family:arial,sans-serif;font-size:small;color:rgb(0,0,0)">Quote:</div><div class="gmail_default" style="font-family:arial,sans-serif;font-size:small;color:rgb(0,0,0)"><h2 id="m_-8919004972116846553m_-4314626392230392525m_8309976769224986166gmail-wont-ai-eventually-be-able-to-do-everything"><font size="4">Won’t AI Eventually Be Able to Do Everything?</font></h2>
<p>Particularly given its recent surprise successes, there’s a somewhat
widespread belief that eventually AI will be able to “do everything”, or
at least everything we currently do. So what about science? Over the
centuries we humans have made incremental progress, gradually building
up what’s now essentially the single largest intellectual edifice of our
civilization. But despite all our efforts, there are still all sorts of
scientific questions that remain. So can AI now come in and just solve
all of them? <br></p><p>--<font size="2">--------------------</font></p><p><font size="2">This is a very long article, so I asked Claude3 AI to summarise it and then comment on the article.</font></p><p><font size="2">BillK</font></p><p><font size="2"><br></font></p><p>I have read through Stephen Wolfram's article "Can AI Solve Science?" The main points and my thoughts are as follows:<br><br>Summary:<br>- Wolfram argues that AI, and in particular large language models (LLMs), have the potential to significantly accelerate scientific discovery and possibly "solve" many open problems in science.<br>- He sees LLMs as having the ability to assimilate and connect vast amounts of scientific knowledge, and to use that to make novel inferences, predictions and discoveries. <br>- Wolfram believes we are on the cusp of an era where AI will become an indispensable tool for science, augmenting and extending human scientific capabilities.<br>- However, he acknowledges current limitations, such as LLMs sometimes generating incorrect or inconsistent outputs. He sees these issues as solvable with further AI progress.<br>- Wolfram envisions a future scientific workflow deeply integrated with AI - scientists using LLMs to rapidly explore ideas, generate hypotheses, analyze data, and more. But with human scientists still in the loop to guide the process.<br><br>Discussion:<br>Wolfram makes a compelling case for the potential of AI to supercharge the scientific process. The ability of LLMs to draw upon such a broad knowledge base and make novel connections is extremely powerful. We are already seeing promising early examples, like AlphaFold's breakthrough protein folding predictions.<br><br>At the same time, I believe Wolfram may be overstating the near-term potential to "solve science" with AI. Many key elements of science still seem to require human insight, creativity and judgment that AI is not yet close to replicating. Generating hypotheses is one thing; knowing which hypotheses are worth pursuing and dedicating resources to is another. <br><br>Current LLMs also have a tendency to sound very authoritative even when wrong. Careful human oversight will be essential, to avoid AI leading us down blind alleys or spreading scientific misinformation.<br><br>Additionally, many cutting-edge scientific domains like quantum physics involve extremely complex mathematics that today's LLMs can't fully grasp or work with. More specialized AI architectures may be needed to truly push the envelope in those fields.<br><br>So in summary, while I'm highly optimistic about AI as an incredible tool to accelerate science, I suspect we are still quite far from the point where AI can autonomously make Nobel-prize worthy discoveries that have eluded human scientists. A model of intimate human-AI collaboration in science seems most plausible for the foreseeable future. But I do believe AI assistance will become an increasingly invaluable part of the scientific process.</p><p>---------------------------------<br></p><p><font size="2"><br></font></p><p><br></p><p><br></p><p><br></p></div><div class="gmail_default" style="font-family:arial,sans-serif;font-size:small;color:rgb(0,0,0)">
<div>
<div id="m_-8919004972116846553m_-4314626392230392525m_8309976769224986166gmail-gpt-stripe" style="background:rgba(246,252,255,0.53);padding:0.75rem 1.5rem;border:1px solid rgba(174,204,217,0.53);font-family:"Source Sans Pro",sans-serif;margin-bottom:2.5rem;max-width:620px;display:none;min-height:0px;height:0px">
<p style="font-size:0.85rem;color:rgb(63,95,106);line-height:1.5;padding-bottom:0px;display:block"><i><br></i></p></div></div></div></div>
_______________________________________________<br>
extropy-chat mailing list<br>
<a href="mailto:extropy-chat@lists.extropy.org" target="_blank">extropy-chat@lists.extropy.org</a><br>
<a href="http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat" rel="noreferrer" target="_blank">http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat</a><br>
</blockquote></div>