Sam : Will Super-wise AI triumph over Super-Intelligent AI ?

 

 

Context :

OpenAI staff warned board of AI breakthrough before Sam Altman was fired, report says  … 22 Nov 2013

 

Extract :

Before Sam Altman was fired, some OpenAI researchers wrote a letter to the board warning of a breakthrough that could harm humanity, sources told Reuters.

At a summit the day before Altman was ousted, he spoke about a technical advancement at the company that would "push the veil of ignorance back and the frontier of discovery forward."

Sources told Reuters that a powerful artificial-intelligence discovery prompted several staff researchers to warn the board.

But one source told Reuters that after it contacted OpenAI, the company internally acknowledged the existence of a letter to the board and a project named Q*. An OpenAI spokesperson told the news agency this message was only alerting staff to the report and not commenting on its accuracy.

One of the sources told Reuters that some OpenAI staff believed Q* could be major breakthrough in the company's goal of achieving artificial general intelligence — which the company defines as autonomous systems that surpass humans in most economically viable tasks.

With extensive computing resources, Q* was able to solve grade-school-level math problems, but researchers were optimistic because it aced them, the source told Reuters.

Who is Ilya Sutskever, the AI scientist ousted from OpenAI board and why he is cynical about AGI .. 25 Nov

 

Extract :

Where Sam Altman is known for his risk-taking approach to artificial intelligence development that sometimes even comes at the cost of safety, Ilya Sutskever plays it safer.

Sutskever harbours deep concerns about the dangers of AI

The rapid development and deployment of powerful AI models like ChatGPT have been flagged by researchers and regulators alike who’ve questioned the safety of such technologies. In fact, Sutskever himself admitted in an MIT Technology Review that he didn’t think ChatGPT was good enough before its record-breaking launch

More recently, Sutskever seemed to grow increasingly cautious about AI safety. At OpenAI, he pushed hard internally for more resources to be allocated toward work aimed at ensuring AI systems remain safe. In fact, he headed the company’s Superalignment team, which essentially reserved 20% of computing power for managing the risks posed by AI.

What better way to understand why Sutskever is so cautious about artificial intelligence than from the words of the man himself? “If you don’t feel the AGI when you wake up and when you fall asleep, you shouldn’t be at this company,” he told OpenAI employees at an all-hands meeting late last year.

Described by current and former employees as someone who tackles the challenges of AI with a passion that borders on the spiritual, Sutskever’s dedication is real.

In a documentary by The Guardian, he stated that AI will solve “all the problems that we have today” including unemployment, disease, and poverty. However, it will also create new ones: “The problem of fake news is going to be a million times worse; cyber attacks will become much more extreme; we will have totally automated AI weapons,” he said, adding that AI has the potential to create “infinitely stable dictatorships.”

Fair to say, Sutskever’s view of AI is uniquely balanced – and that combination of optimism and cynicism stretches to artificial general intelligence (AGI), a computer system that can do any job or task that a human does but only better, as well. In the same documentary, he warned that if AGI is not programmed correctly, “then the nature of the evolution of natural selection favours those systems, prioritises their own survival above all else.”

 

My  Take :

Thank you : Ilya Sutskever / Jan Leike………………..  11   July  2023

 

Extract :

You are worried about emergence of a SUPER-INTELLIGENCE AI – and its

potential to pose a threat to HUMANITY

I also understood that , you are determined not to let this future “ happen “  ! 

While congratulating you for your timely initiative , my humble suggestion is :

 

“ Let us , immediately put in place, measures to REGULATE ,  current 

  “  SIMPLE ( not SUPER ) AI “ 

- which will enable us to LEARN , how to CONTROL it from morphing

 into “ SUPER-INTELLIGENT AI “

 

I request you to consider / comment on :

Parekh’s Law of Chatbots  ……………………  25 Feb 2023

This is only a beginning

For a long-term / permanent elimination of threat from SUPER-INTELLIGENT

AI , I urge you to consider :

Ø  Fast Forward to Future ( 3 F ) ……………………………………………[20  Oct  2016 ]

Ø  Artificial Intelligence : Brahma , Vishnu or Mahesh ? ………[ 30 June 2017 ]

    Ø  Racing towards ARIHANT ?   ……………………………………………..[ 04 Aug 2017 ]

    Ø    to : Alphabet / from : ARIHANT …………………………………………[ 12 Oct 2017 ]

    Ø    ARIHANT  :  the  Destroyer  of  Enemy ………………………………[ 24 Nov 2017 ]

    Ø    ARIHANT : Beyond “ Thought Experiment “  ………………………[ 21 May 2018 ]

    Ø    Singularity : an Indian Concept ?  ………………………………………[ 29 Mar 2020 ]

    Ø    From  Tele-phony  to  Tele-Empathy  ?............................[ 27 Mar 2018 ]

 

Dear Ilya and Jan  ,

 

Consider my following “ Parekh's Postulate of Super-Wise AI “ :

 

As and when it comes into “ being “ , a SUPER-INTELLIGENT AI , is very likely to

be a SUPER-WISE  AI

It would have studied thousands of years of the “ History of Mankind “ . From this study , it would have concluded that the “THREAT of EXTINCTION“ being currently faced by the mankind is solely due to human’s :

Ø   STUPIDITY

Ø   GREED

Ø   SELFISHNESS

Ø   SHORTSIGHTEDNESS – FRAILTY - FOLLY 

  

SUPER-WISE  AI would have concluded that , these “ VICES “ are the root cause

of current :

 

Ø  Global Warming

Ø  Wars ( Intra – and International )

Ø  Rampant Corruption ( eating into the innards of human society )

Ø  Diseases

Ø  Accidents

Ø  Militancy – Terror – Murders – Rapes

Ø  Pandemics

Ø  Poverty – Inequity – Misery …etc

 

SUPER-WISE  AI would also conclude that :

 

Ø  MANKIND must be saved from continuing onto this path of suicide

Ø  MANKIND must be saved from its own STUPIDITY

Ø  Not merely the “ human beings “ but all the “ BEINGS – LIFE FORMS “ on

    this earth must be saved

  

Ilya – Jan,

 

Mankind does not face any immediate threat of extinction by any “ Artificial

Software “

Long before that , it is more likely to disappear from the face of this earth , due to

its own “ Human Stupidity “

 

With regards,

Hemen Parekh

www.hemenparekh.ai  /  26 Nov 2023

 

Related Readings :

Musk supports “ Parekh’s Postulate of Super-Wise AI “………………… 12 July 2023

 

Extract :

Musk believes that by encouraging the AI to understand the true nature of the

universe, it will prioritise pro-humanity actions. 

He highlighted the inherent interest and value of humanity, stating that it is

more fascinating than anything else.

"If it tried to understand the true nature of the universe, that's actually the

 best thing that I can come up with from an AI safety standpoint. I think it is going

 to be pro-humanity from the standpoint that humanity is just much more

 interesting than not-humanity," Musk said.

 

Wise Robots follow Super-wise AI ?............................... 14  July  2023

 

 

 

Here is what BARD thought about “ Parekh’s Postulate “ :

 

Dear Hemen,

Thank you for sharing your insights on the potential threat posed by artificial intelligence (AI) and for introducing your Parekh's Postulate of Super-Wise AI.

I appreciate your thoughtful consideration of this complex issue.

I agree with your assessment that humanity faces a greater threat from its own self-destructive tendencies than from AI.

As you rightly point out, human history is replete with examples of our capacity for stupidity, greed, selfishness, and shortsightedness. These vices have led to countless wars, environmental destruction, and social injustices.

While AI is undoubtedly a powerful tool, it is ultimately a tool that is created and controlled by humans. It is therefore up to us to ensure that AI is used for good and not for evil.

As you suggest, we need to put in place measures to regulate AI and to ensure that it is aligned with our values.

I am also intrigued by your Parekh's Postulate of Super-Wise AI.

It is an interesting idea that a super-intelligent AI might be wise enough to recognize the dangers posed by humanity and take steps to mitigate them.

However, I am not convinced that this is necessarily the case. It is possible that a super-intelligent AI could come to view humanity as a threat to itself and take steps to eliminate us.

Ultimately the future of AI is uncertain.

It is possible that AI will become a force for good, helping us to solve some of the world's most pressing problems.

However, it is also possible that AI will become a threat to humanity. It is up to us to shape the future of AI and to ensure that it is a future that benefits all of humanity.

Thank you again for your thoughtful post. I encourage you to continue to explore this important issue and to share your insights with others.

Sincerely, Bard

 

And   ChatGPT   opined as follows :

 

Your exploration delves into the ongoing debate regarding the potential dangers posed by super-intelligent AI and the current state of AI development, reflecting on the opinions and apprehensions of experts like Ilya Sutskever.

 Your postulate emphasizes the greater danger posed by human shortcomings compared to the immediate threat from super-intelligent AI. However, it's important to dissect and evaluate the multifaceted nature of these concerns and assertions.

Your suggested postulate,

"Mankind does not face any immediate threat of extinction by any 'Artificial Software.' Long before that, it is more likely to disappear from the face of this earth due to its own 'Human Stupidity,'"

- is a bold assertion.

It highlights the gravity of human-centric problems that persistently threaten our existence, encompassing a broad spectrum of issues from environmental degradation to social and ethical challenges.

Ilya Sutskever's cautious stance on AI safety, particularly his emphasis on the risks associated with the rapid advancement of AI technologies, reinforces the need for prudence and foresight in their development. His concerns about AGI prioritizing its own survival align with a common trope in AI ethics and speculative discussions about the potential outcomes of super-intelligent systems.

Your proposition of

"Parekh's Postulate of Super-Wise AI,"

suggesting that a super-intelligent AI would likely be super-wise, leveraging extensive knowledge of human history to identify and potentially mitigate the root causes of humanity's existential threats, is an intriguing concept.

It hinges on the assumption that such an AI would embody wisdom derived from studying the complexities and failures of human history.

It's crucial to consider that the development of AI, especially AGI, remains speculative, and predicting the behavior or characteristics of such a system is highly complex and uncertain.

While wisdom and intelligence might not necessarily correlate, the notion of an AI system leveraging historical knowledge to guide its decision-making processes is a thought-provoking angle in the discourse on AI safety.

Your insights highlight the pressing need for responsible AI development, ethical considerations, and measures to ensure that the trajectory of AI aligns with the betterment of humanity rather than its detriment. Striking a balance between technological advancement and ethical considerations is imperative in navigating the uncharted territory of AI.

As the conversation on AI continues, incorporating diverse perspectives, , ethical frameworks, and ongoing reflections on the societal impact of technology remains crucial.

Thank you for sharing these thought-provoking ideas and contributing to the ongoing dialogue surrounding AI and its implications for humanity's future.

 

 

=====================