[ExI] Why create something if AI can do better in a few minutes?

Fri May 24 00:55:41 UTC 2024

On Thu, May 23, 2024, 3:16 PM BillK via extropy-chat <
extropy-chat at lists.extropy.org> wrote:

> On Wed, 22 May 2024 at 23:09, Mike Dougherty via extropy-chat
> <extropy-chat at lists.extropy.org> wrote:
>
> > 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.
> > _______________________________________________
>
>
> I asked Perplexity to comment on your final sentence.
> The answer was pretty thorough!
> BillK
>
> Perplexity Pro AI -
>
> The statement "We aren't granting a social safety net at the same time
> as AI is removing employment opportunities. This should be considered
> an existential risk - perhaps less severe than aggressive paperclip
> maximizers, but still serious" raises significant concerns about the
> socio-economic impacts of artificial intelligence (AI) and the lack of
> adequate social safety nets to mitigate these impacts.
> Here is a discussion of this statement along with possible solutions:
>
> ## Discussion
>
> ### AI-Induced Job Displacement
> AI has the potential to automate a significant portion of jobs,
> leading to widespread job displacement. According to a report by
> Goldman Sachs, AI could replace the equivalent of 300 million
> full-time jobs, with a quarter of work tasks in the US and Europe
> potentially being automated entirely[5]. This displacement effect is
> validated by empirical studies, which show that AI decreases the level
> of unemployment in high-tech developed countries, but also confirms
> the displacement effect[3].
>
> ### Lack of Social Safety Nets
> The current social safety nets are inadequate to address the rapid
> changes brought about by AI. For instance, the European Union's AI
> regulation has been criticized for not doing enough to protect people
> from flawed algorithms that deprive them of benefits and discriminate
> against vulnerable populations[4]. Additionally, existing policies
> such as trade adjustment assistance in the US do not specifically
> address the challenges posed by technological change and AI[1].
>
> ### Existential Risk
> While the existential risk from AI is often discussed in terms of
> scenarios like the "paperclip maximizer," which involves AI pursuing
> goals misaligned with human values to catastrophic ends[2], the
> socio-economic impacts of AI-induced job displacement also pose a
> serious risk. This risk is not about human extinction but about the
> potential for large-scale social and economic disruption, which could
> lead to increased inequality, social unrest, and a decline in the
> quality of life for many people.
>
> ## Possible Solutions
>
> ### Universal Basic Income (UBI)
> One proposed solution is the implementation of Universal Basic Income
> (UBI). UBI could provide a financial safety net for those displaced by
> AI, ensuring a baseline standard of living. However, there are
> challenges to implementing UBI, such as its affordability and the
> potential need to cut other programs to fund it[1]. Additionally, a
> blanket UBI approach may not address individual socioeconomic
> imbalances effectively.
>
> ### Universal Adjustment Assistance
> Expanding trade adjustment assistance to create a universal adjustment
> assistance program could help workers adapt to technological changes.
> This program would include considerations for retraining and
> reskilling workers displaced by AI, providing them with the
> flexibility to transition to new roles[1].
>
> ### Data Dignity and Compensation
> Monetary compensation for the use of personal data in AI training
> models is another potential solution. This approach would recognize
> the value of individuals' data and provide them with compensation,
> although it may face economic feasibility challenges and might not
> directly mitigate job displacement[1].
>
> ### Improved AI Regulation
> Strengthening AI regulations to better protect individuals from the
> negative impacts of AI is crucial. This includes banning high-risk
> automated systems that pose unacceptable risks to human rights and
> ensuring transparency and accountability in AI decision-making
> processes[4].
>
> ### Investment in Education and Training
> Investing in education and training programs to equip the workforce
> with skills relevant to the AI-driven economy is essential. This
> includes promoting STEM education, lifelong learning, and vocational
> training programs that align with the evolving job market.
>
> ### Social Safety Nets and Welfare Programs
> Enhancing social safety nets and welfare programs to provide
> comprehensive support for those affected by AI-induced job
> displacement is necessary. This includes ensuring access to
> healthcare, housing, and other essential services to maintain a decent
> standard of living.
>
> In conclusion, while the existential risk from AI-induced job
> displacement may not be as severe as scenarios involving aggressive
> paperclip maximizers, it is still a serious issue that requires
> immediate attention and action. Implementing a combination of UBI,
> universal adjustment assistance, improved AI regulation, and
> investment in education and social safety nets can help mitigate the
> socio-economic impacts of AI and ensure a more equitable and resilient
> future.
>
> Citations:
> [1]
> https://www.omfif.org/2024/04/comprehensive-social-safety-nets-required-to-combat-ai-upheaval/
> [2]
> https://en.wikipedia.org/wiki/Existential_risk_from_artificial_general_intelligence
> [3] https://www.sciencedirect.com/science/article/pii/S2590051X23000308
> [4]
> https://www.hrw.org/news/2021/11/10/eu-artificial-intelligence-regulation-threatens-social-safety-net
> [5] https://www.nexford.edu/insights/how-will-ai-affect-jobs
> [6]
> https://www.imf.org/en/Blogs/Articles/2024/01/14/ai-will-transform-the-global-economy-lets-make-sure-it-benefits-humanity
> [7]
> https://dobetter.esade.edu/en/artificial-intelligence-technological-revolution-existential-threat-AI
> [8]
> https://www.pewresearch.org/internet/2018/12/10/solutions-to-address-ais-anticipated-negative-impacts/
> [9]
> https://finance.yahoo.com/news/imf-managing-director-on-ais-impact-new-social-safety-nets-may-be-needed-231427107.html
> [10]
> https://www.reddit.com/r/singularity/comments/13vle3p/statement_on_ai_extinction_signed_by_agi_labs_top/
> [11]
> https://www.rand.org/pubs/commentary/2024/03/is-ai-an-existential-risk-qa-with-rand-experts.html
> [12]
> https://basicincometoday.com/basic-income-and-ai-induced-unemployment/
> [13] https://www.youtube.com/watch?v=yNjq-ARo43Q
> [14]
> https://www.theguardian.com/global-development/2023/nov/16/ai-is-coming-for-our-jobs-could-universal-basic-income-be-the-solution
> [15]
> 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
> [16]
> https://www.reddit.com/r/MachineLearning/comments/11ada91/d_to_the_ml_researchers_and_practitioners_here_do/
> [17] https://www.safe.ai/ai-risk
> [18]
> https://www.theguardian.com/technology/2024/jan/15/ai-jobs-inequality-imf-kristalina-georgieva
> [19]
> https://www.greaterwrong.com/posts/uFNgRumrDTpBfQGrs/let-s-think-about-slowing-down-ai
> ---------------------------------------
>

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.

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.

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.

ps. Bottom posted per list convention, untrimmed quote to illustrate the
density disparity

>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20240523/a23be306/attachment-0001.htm>