<div dir="auto"><div><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Thu, May 23, 2024, 3:16 PM BillK via extropy-chat <<a href="mailto:extropy-chat@lists.extropy.org">extropy-chat@lists.extropy.org</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">On Wed, 22 May 2024 at 23:09, Mike Dougherty via extropy-chat<br>
<<a href="mailto:extropy-chat@lists.extropy.org" target="_blank" rel="noreferrer">extropy-chat@lists.extropy.org</a>> wrote:<br><br>
> That we aren't granting a social safety net at the same time we are removing employment opportunities should be considered an existential risk - perhaps less severe than aggressive paperclip maximizes, but still serious.<br>
> _______________________________________________<br>
<br>
<br>
I asked Perplexity to comment on your final sentence.<br>
The answer was pretty thorough!<br>
BillK<br>
<br>
Perplexity Pro AI -<br>
<br>
The statement "We aren't granting a social safety net at the same time<br>
as AI is removing employment opportunities. This should be considered<br>
an existential risk - perhaps less severe than aggressive paperclip<br>
maximizers, but still serious" raises significant concerns about the<br>
socio-economic impacts of artificial intelligence (AI) and the lack of<br>
adequate social safety nets to mitigate these impacts.<br>
Here is a discussion of this statement along with possible solutions:<br>
<br>
## Discussion<br>
<br>
### AI-Induced Job Displacement<br>
AI has the potential to automate a significant portion of jobs,<br>
leading to widespread job displacement. According to a report by<br>
Goldman Sachs, AI could replace the equivalent of 300 million<br>
full-time jobs, with a quarter of work tasks in the US and Europe<br>
potentially being automated entirely[5]. This displacement effect is<br>
validated by empirical studies, which show that AI decreases the level<br>
of unemployment in high-tech developed countries, but also confirms<br>
the displacement effect[3].<br>
<br>
### Lack of Social Safety Nets<br>
The current social safety nets are inadequate to address the rapid<br>
changes brought about by AI. For instance, the European Union's AI<br>
regulation has been criticized for not doing enough to protect people<br>
from flawed algorithms that deprive them of benefits and discriminate<br>
against vulnerable populations[4]. Additionally, existing policies<br>
such as trade adjustment assistance in the US do not specifically<br>
address the challenges posed by technological change and AI[1].<br>
<br>
### Existential Risk<br>
While the existential risk from AI is often discussed in terms of<br>
scenarios like the "paperclip maximizer," which involves AI pursuing<br>
goals misaligned with human values to catastrophic ends[2], the<br>
socio-economic impacts of AI-induced job displacement also pose a<br>
serious risk. This risk is not about human extinction but about the<br>
potential for large-scale social and economic disruption, which could<br>
lead to increased inequality, social unrest, and a decline in the<br>
quality of life for many people.<br>
<br>
## Possible Solutions<br>
<br>
### Universal Basic Income (UBI)<br>
One proposed solution is the implementation of Universal Basic Income<br>
(UBI). UBI could provide a financial safety net for those displaced by<br>
AI, ensuring a baseline standard of living. However, there are<br>
challenges to implementing UBI, such as its affordability and the<br>
potential need to cut other programs to fund it[1]. Additionally, a<br>
blanket UBI approach may not address individual socioeconomic<br>
imbalances effectively.<br>
<br>
### Universal Adjustment Assistance<br>
Expanding trade adjustment assistance to create a universal adjustment<br>
assistance program could help workers adapt to technological changes.<br>
This program would include considerations for retraining and<br>
reskilling workers displaced by AI, providing them with the<br>
flexibility to transition to new roles[1].<br>
<br>
### Data Dignity and Compensation<br>
Monetary compensation for the use of personal data in AI training<br>
models is another potential solution. This approach would recognize<br>
the value of individuals' data and provide them with compensation,<br>
although it may face economic feasibility challenges and might not<br>
directly mitigate job displacement[1].<br>
<br>
### Improved AI Regulation<br>
Strengthening AI regulations to better protect individuals from the<br>
negative impacts of AI is crucial. This includes banning high-risk<br>
automated systems that pose unacceptable risks to human rights and<br>
ensuring transparency and accountability in AI decision-making<br>
processes[4].<br>
<br>
### Investment in Education and Training<br>
Investing in education and training programs to equip the workforce<br>
with skills relevant to the AI-driven economy is essential. This<br>
includes promoting STEM education, lifelong learning, and vocational<br>
training programs that align with the evolving job market.<br>
<br>
### Social Safety Nets and Welfare Programs<br>
Enhancing social safety nets and welfare programs to provide<br>
comprehensive support for those affected by AI-induced job<br>
displacement is necessary. This includes ensuring access to<br>
healthcare, housing, and other essential services to maintain a decent<br>
standard of living.<br>
<br>
In conclusion, while the existential risk from AI-induced job<br>
displacement may not be as severe as scenarios involving aggressive<br>
paperclip maximizers, it is still a serious issue that requires<br>
immediate attention and action. Implementing a combination of UBI,<br>
universal adjustment assistance, improved AI regulation, and<br>
investment in education and social safety nets can help mitigate the<br>
socio-economic impacts of AI and ensure a more equitable and resilient<br>
future.<br>
<br>
Citations:<br>
[1] <a href="https://www.omfif.org/2024/04/comprehensive-social-safety-nets-required-to-combat-ai-upheaval/" rel="noreferrer noreferrer" target="_blank">https://www.omfif.org/2024/04/comprehensive-social-safety-nets-required-to-combat-ai-upheaval/</a><br>
[2] <a href="https://en.wikipedia.org/wiki/Existential_risk_from_artificial_general_intelligence" rel="noreferrer noreferrer" target="_blank">https://en.wikipedia.org/wiki/Existential_risk_from_artificial_general_intelligence</a><br>
[3] <a href="https://www.sciencedirect.com/science/article/pii/S2590051X23000308" rel="noreferrer noreferrer" target="_blank">https://www.sciencedirect.com/science/article/pii/S2590051X23000308</a><br>
[4] <a href="https://www.hrw.org/news/2021/11/10/eu-artificial-intelligence-regulation-threatens-social-safety-net" rel="noreferrer noreferrer" target="_blank">https://www.hrw.org/news/2021/11/10/eu-artificial-intelligence-regulation-threatens-social-safety-net</a><br>
[5] <a href="https://www.nexford.edu/insights/how-will-ai-affect-jobs" rel="noreferrer noreferrer" target="_blank">https://www.nexford.edu/insights/how-will-ai-affect-jobs</a><br>
[6] <a href="https://www.imf.org/en/Blogs/Articles/2024/01/14/ai-will-transform-the-global-economy-lets-make-sure-it-benefits-humanity" rel="noreferrer noreferrer" target="_blank">https://www.imf.org/en/Blogs/Articles/2024/01/14/ai-will-transform-the-global-economy-lets-make-sure-it-benefits-humanity</a><br>
[7] <a href="https://dobetter.esade.edu/en/artificial-intelligence-technological-revolution-existential-threat-AI" rel="noreferrer noreferrer" target="_blank">https://dobetter.esade.edu/en/artificial-intelligence-technological-revolution-existential-threat-AI</a><br>
[8] <a href="https://www.pewresearch.org/internet/2018/12/10/solutions-to-address-ais-anticipated-negative-impacts/" rel="noreferrer noreferrer" target="_blank">https://www.pewresearch.org/internet/2018/12/10/solutions-to-address-ais-anticipated-negative-impacts/</a><br>
[9] <a href="https://finance.yahoo.com/news/imf-managing-director-on-ais-impact-new-social-safety-nets-may-be-needed-231427107.html" rel="noreferrer noreferrer" target="_blank">https://finance.yahoo.com/news/imf-managing-director-on-ais-impact-new-social-safety-nets-may-be-needed-231427107.html</a><br>
[10] <a href="https://www.reddit.com/r/singularity/comments/13vle3p/statement_on_ai_extinction_signed_by_agi_labs_top/" rel="noreferrer noreferrer" target="_blank">https://www.reddit.com/r/singularity/comments/13vle3p/statement_on_ai_extinction_signed_by_agi_labs_top/</a><br>
[11] <a href="https://www.rand.org/pubs/commentary/2024/03/is-ai-an-existential-risk-qa-with-rand-experts.html" rel="noreferrer noreferrer" target="_blank">https://www.rand.org/pubs/commentary/2024/03/is-ai-an-existential-risk-qa-with-rand-experts.html</a><br>
[12] <a href="https://basicincometoday.com/basic-income-and-ai-induced-unemployment/" rel="noreferrer noreferrer" target="_blank">https://basicincometoday.com/basic-income-and-ai-induced-unemployment/</a><br>
[13] <a href="https://www.youtube.com/watch?v=yNjq-ARo43Q" rel="noreferrer noreferrer" target="_blank">https://www.youtube.com/watch?v=yNjq-ARo43Q</a><br>
[14] <a href="https://www.theguardian.com/global-development/2023/nov/16/ai-is-coming-for-our-jobs-could-universal-basic-income-be-the-solution" rel="noreferrer noreferrer" target="_blank">https://www.theguardian.com/global-development/2023/nov/16/ai-is-coming-for-our-jobs-could-universal-basic-income-be-the-solution</a><br>
[15] <a href="https://www.linkedin.com/pulse/over-80-jobs-risk-due-ai-becoming-existential-threat-humanity-gi9ke?trk=organization_guest_main-feed-card_feed-article-content" rel="noreferrer noreferrer" target="_blank">https://www.linkedin.com/pulse/over-80-jobs-risk-due-ai-becoming-existential-threat-humanity-gi9ke?trk=organization_guest_main-feed-card_feed-article-content</a><br>
[16] <a href="https://www.reddit.com/r/MachineLearning/comments/11ada91/d_to_the_ml_researchers_and_practitioners_here_do/" rel="noreferrer noreferrer" target="_blank">https://www.reddit.com/r/MachineLearning/comments/11ada91/d_to_the_ml_researchers_and_practitioners_here_do/</a><br>
[17] <a href="https://www.safe.ai/ai-risk" rel="noreferrer noreferrer" target="_blank">https://www.safe.ai/ai-risk</a><br>
[18] <a href="https://www.theguardian.com/technology/2024/jan/15/ai-jobs-inequality-imf-kristalina-georgieva" rel="noreferrer noreferrer" target="_blank">https://www.theguardian.com/technology/2024/jan/15/ai-jobs-inequality-imf-kristalina-georgieva</a><br>
[19] <a href="https://www.greaterwrong.com/posts/uFNgRumrDTpBfQGrs/let-s-think-about-slowing-down-ai" rel="noreferrer noreferrer" target="_blank">https://www.greaterwrong.com/posts/uFNgRumrDTpBfQGrs/let-s-think-about-slowing-down-ai</a><br>
---------------------------------------<br></blockquote></div></div><div dir="auto"><br></div><div dir="auto">So if instead of an information/keyword -dense sentence (that I wrote) there is several pages of "more words" (that AI wrote) ... but I assumed my audience knew all those info-tokens already; and I would not presume to explain any of those ideas without being asked for clarification. </div><div dir="auto"><br></div><div dir="auto">If your intent was to test that AI du jour was able to unpack that density, then i agree it did cover the gist. However, there wasn't any new insight added to the conversation. If something else, please do educate me. </div><div dir="auto"><br></div><div dir="auto">fwiw, I'm not trying to be difficult. I would like to understand why people yield the opportunity to participate in social interaction to overwhelming spew of AI generated parrot chatter. It's not that I am unwilling to entertain AI at our dinner table - I'm trying to clarify my current location in the infoverse and asking for direction to a new understanding of the neighborhood. </div><div dir="auto"><br></div><div dir="auto">ps. Bottom posted per list convention, untrimmed quote to illustrate the density disparity</div><div dir="auto"><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
</blockquote></div></div></div>