Sunday, 2 April 2023

Sam Altman : Man on a Mission

Context :

The ChatGPT King Isn’t Worried, but He Knows You Might Be

( NY Times / 31 Mar 2023 (By Cade Metz )

Extract :

I first met Sam Altman in the summer of 2019, days after Microsoft agreed to invest $1 billion in his three-year-old start-up, OpenAI. At his suggestion, we had dinner at a small, decidedly modern restaurant not far from his home in San Francisco.

Halfway through the meal, he held up his iPhone so I could see the contract he had spent the last several months negotiating with one of the world’s largest tech companies. It said Microsoft’s billion-dollar investment would help OpenAI build what was called artificial general intelligence, or A.G.I., a machine that could do anything the human brain could do.

Later, as Mr. Altman sipped a sweet wine in lieu of dessert, he compared his company to the Manhattan Project.

As if he were chatting about tomorrow’s weather forecast, he said the U.S. effort to build an atomic bomb during the Second World War had been a “project on the scale of OpenAI — the level of ambition we aspire to.”

He believed A.G.I. would bring the world prosperity and wealth like no one had ever seen.

He also worried that the technologies his company was building could cause serious harm — spreading disinformation, undercutting the job market. Or even destroying the world as we know it.

“I try to be upfront,” he said. “Am I doing something good ? Or really bad ?”

In 2019, this sounded like science fiction.

In 2023, people are beginning to wonder if Sam Altman was more prescient than they realized.

Now that OpenAI has released an online chatbot called ChatGPT, anyone with an internet connection is a click away from technology:

# that will answer burning questions about organic chemistry,

# write a 2,000-word term paper on Marcel Proust and his madeleine or

# even generate a computer program that drops digital snowflakes across a laptop screen

— all with a skill that seems human.

As people realize that this technology is also a way of spreading falsehoods or even persuading people to do things they should not do, some critics are accusing Mr. Altman of reckless behavior.

This past week, more than a thousand A.I. experts and tech leaders called on OpenAI and other companies to

pause their work on systems like ChatGPT, saying they present “profound risks to society and humanity.”

Now let us read what Sam wrote to me ( through Facebook Messenger ) :

I wrote to Sam :

Sat 2:09 PM

AI – the new WMD ? History repeats itself

ChatGPT replied Parekh's Law of Chatbots is a step in the right direction, and it is

feasible to implement such regulation

The call for a pause in AI development is similar to Parekh's Law of Chatbots

Sam replied :

Sun 1:50 AM

Well that was expected to happen sometime if not now later, that's why we've

already started doing that in our firm where have few months downtime on all our

programs to give independent labs opportunity to implement safety

protocols which are audited and overseen by outside experts.

Risk and return are always related, but here the advantages outweigh the

negatives which in general are always outlined so there were mitigated before the

launch of our first models.

There're little to no disadvantages when it comes to our products, as the reason

why it was created was to tackle the potential risks associated with developing AI

technologies that could be misused or abused.

As a result, we founded OpenAI with the goal of creating safe, beneficial AI

that would be developed and deployed in an ethical and responsible manner.

Our model doesn't fall under that as it's designed to assist and augment human

work, not to threaten jobs.

While it is true that AI and automation can sometimes replace certain types of

jobs, it is important to note that the goal of AI is to increase efficiency and

productivity, which can lead to new job opportunities and innovations.

I wrote back :

Sun 10:50 AM

Sam

Many thanks for your prompt and elaborate response

It is deeply reassuring that all the AI development taking place at OpenAI, is

guided by a Moral Compass

From what you write, it becomes amply clear that OpenAI is right up front,

settling Benchmarks of Social Responsibility, which all other developers will be

compelled to follow

I seek your permission to reproduce your comments in my next blog

Best wishes and regards, Hemen / 02 April 2023

Sam replied :

Sun 6:32 PM

You're permitted my friend:-)

I also have an advice you can attach to the footer

My advice would be any technocrat looking to vest into this space and help forge

our pathway to the new dawn.

Take a look at this site( orderbooks.co ) to be part of this advocate !

Dreams do come true.

With regards,

Hemen Parekh

www.hemenparekh.ai / 03 April 2023

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

Saturday, 1 April 2023

AI – the new WMD ? History repeats itself

As Elon Musk Calls For A ‘Pause’ On AI Development, Will The AI Wars Reach A Temporary Truce?

[ Forbes / 30 March 2023 ]

Extract :

Key takeaways

· Future of Life Institute backed by Elon Musk, Apple co-founder Steve Wozniak and DeepMind engineers has called for an immediate pause on developing advanced AIs

· OpenAI founder Sam Altman and Microsoft founder Bill Gates have both warned about AI advancements, but companies have been rewarded with stock price bumps

· No legal or regulatory framework for AI exists as of yet

Could the AI wars come to a crashing halt? Yes, if Elon Musk gets his way. The billionaire, other tech leaders and AI engineers have published an open letter calling for an immediate six-month pause in progressing AI tech, so regulation can come in.

OpenAI and Bill Gates have warned on the risks of AI, so everyone’s singing from the same hymn sheet, but the Future of Life Institute has taken things a step further. The question is - will Big Tech pay attention? Let’s look at what the letter said, whether AI risks going off the rails and what it means for investors.

What does the open letter say?

Elon Musk is not pulling punches when it comes to AI development. He and almost 1300 other AI experts and researchers have published an open letter calling for all AI labs to immediately pause “the training of AI systems more powerful than GPT-4”, OpenAI’s latest chatbot iteration, until regulatory frameworks are established

According to the letter, the pause should be for at least six months, include ‘all key actors’ publicly announcing their intentions and involve government intervention should the pause not happen quickly.

The letter was published by the Future of Life Institute, which lists Elon as an external advisor on its website. The letter has been signed by top leaders in the field alongside Musk including Apple co-founder Steve Wozniak, Stability AI founder Emad Mostaque and hundreds of other engineers from DeepMind, Amazon, Meta and Microsoft.

What have other leaders said about AI?

While the call to action is something other commentaries from the likes of Bill Gates and Sam Altman have lacked, all have warned that developing AI needs to be done with an abundance of caution.

The open letter cites Sam Altman’s blog from February this year, where the OpenAI founder discusses the need for government intervention in AI training.

He said “it may be important to get independent review before starting to train future systems, and for the most advanced efforts to agree to limit the rate of growth of compute used for creating new models”.

Bill Gates, the former CEO of Microsoft, had a more upbeat tone in his letter on AI. He singled out education, climate change and healthcare as some of the industries AI had the potential to transform.

But he, too, warned about the need for caution in building AI, saying a lack of safeguards around AGI could have devastating consequences for humankind.

“The world needs to establish the rules of the road so that any downsides of artificial intelligence are far outweighed by its benefits,” he wrote.

Computing giant Microsoft has a $10 billion partnership with OpenAI and has become a surprise leader in the space. Its stock price has climbed 17% since the start of the year to hit highs of $280.

What recent developments have there been in AI?

What’s prompted the open letter is tech companies’ race to outpace one another as this exciting new technology develops.

Google’s Bard AI has now launched, with UK and US users able to sign up to try the ChatGPT competitor. Google has also announced it will be integrating Bard into its Google apps like Sheets, Docs and Meet, but there’s no timescale on that release.

The search engine titan has been chasing Microsoft since its OpenAI announcement.

Microsoft has been announcing AI-infused upgrades to its suite of products at a dizzying pace thanks to its OpenAI investment.

Its newest launch is Microsoft Security Pilot, an AI-powered cybersecurity tool for businesses. Microsoft stock was up 1.5% after the announcement.

Chinese tech company Baidu “pulled a Google” with a rocky launch for its Ernie AI chatbot, with shares dropping 10% on the same day. The share price quickly recovered after it was announced 30,000 companies had signed up to the service, with the stock rallying 14%.

Adobe and Nvidia announced their continued partnership to release Adobe’s generative AI platform, Firefly, which is set to augment its Photoshop and Illustrator tools among others. Adobe stock rose 3.1% after the announcement and Nvidia also saw a 1.2% bump.

It’s been a rocky ride for tech companies developing a ‘future tech’ during an economic downturn. One wrong move and the share prices have come tumbling down, as we saw with Google’s Bard launch. But on the flip side, those who have debuted strong AI products and partnerships have been rewarded with share price bumps.

Should AI development slow down?

The open letter isn’t calling for a complete ban, stating, “This does not mean a pause on AI development in general, merely a stepping back from the dangerous race to ever-larger unpredictable black-box models with emergent capabilities.”

There's no denying there’s a distinct lack of AI regulatory framework. The UK has rejected plans for an AI-specific regulator this week, instead opting for its existing regulators to adopt AI principles guidance. The EU and US are said to be consulting on the matter, but as it stands no AI legislation exists.

At this stage, the public has experienced a taste of how AI can speed up workflows and help with productivity thanks to ChatGPT, Microsoft Bing and Google Bard. Wall Street also expects to see further development from bigger companies as the AI start-ups have already produced the goods.

Pressing the pause button gives companies and government time to address concerns around privacy, algorithmic bias and regulation—and gives the public a chance to get used to AI.

From an investment perspective, it’s likely companies that take a long-term view on AI regulation will fare better when it inevitably comes in. Wall Street will be keeping an eye on those who prioritize AI safety sooner rather than later.

The bottom line

While the tone of the letter is decidedly doom and gloom, it’s to draw attention to the potential risks of developing AI. It sounds like science fiction right now, but the top minds in the field think of it as an inevitability—and so want the brakes on now before the train falls off the tracks.

Governments tend to be slow in dealing with emerging tech, but if they can be convinced of the threat then we could well see a pause take place.

MY TAKE :

USA exploded first atom bomb in 1945

Soon, USA was joined by Russia, UK and other countries

Over the next 30 years, these “ developed countries “ stockpiled thousands of Atom / Hydrogen bombs

Then they realized the danger of a “ runaway race “( to produce atom bombs ) among dozens of countries

So they negotiated to :

Ø Gradually destroy the stockpile of bombs ( some bombs got destroyed but a huge stock survived )

Ø Halt further production of these bombs by ANY country – and coerced many countries to sign up on “ Nuclear Non Proliferation Treaty ( NNPT ) “.

Ø India refused to sign NNPT , insisting that, as a first step , all existing bombs stockpiled by the pioneers, MUST be destroyed. It was totally unfair of USA – Russia etc., to continue to “ hold on “ to their own stockpile while asking other countries NOT to develop their own bombs

Ø At the same time, on its own volition, India declared that :

# All of its Nuclear Programs will be directed towards “ Peaceful Uses “ of nuclear energy

# India will never use a Nuclear Weapon first – but use it only if attacked by one

This UNILATERAL STAND won over hearts of citizen around the World

Now comes following report :

India Can Build Something Equivalent To AI ChatGPT? Ashwini Vaishnaw Says Big Announcement In Few Weeks ……………… ZeeNews / 27 March 2023

Extract :

IT Minister Ashwini Vaishnaw on Monday hinted at a "big announcement" in a few weeks in the context of conversational AI tools. To a specific question on whether India can build something equivalent to the conversational AI tool ChatGPT, the minister said "wait for a few weeks, there will be a big announcement".

When asked about what the big announcement might be, the minister said, "Parliament is in session, so I cannot say anything..." He declined to give further details. Vaishnaw was speaking at the India Global Forum event.

Dear Shri Vaishnawji ,

To be fair, petition does not ask only the newcomers to stop experimenting with

Conversational AI ( aka Chatbots ). It asks everybody . But then OpenAI –

Google etc., are enjoying “ first-mover advantage “ .

Therefore, India must work twice as hard and fast to, not only catch up but

overtake the BIG TECH

No one has any moral right to tell us to give up / slow down on our AI program

But,

As the leader of G 20 this year, we have a unique / golden opportunity to

demonstrate to the World, our “ moral leadership “ of “ Vaudhaiva Kutumbakam (

Whole world is one Family ) , by UNILATERALLY ADOPTING ,

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

Then ask those petitioners to demonstrate their SINCERENESS OF INTENT , by

convening a world-conference to debate and adopt my proposal ( no doubt with

modifications deemed necessary )

Dear Shri Vaishnawji,

It is time to “ Propose “ ( a concrete measure ) instead of just “ Oppose “

It is time to “ Act “ rather than wait for the Government of some other country

act first and then we “ React “

It is time to “ Write History “ rather than letting our future generations, “ Read

History “

And that time is NOW

With regards,

Hemen Parekh

www.hemenparekh.ai / 01 April 2023

“ Parekh’s Law of Chatbot “ is vindicated – by ChatGPT :

My poser to ChatGPT :

In the following blog, I have tried to compare the actual past development of Atom / Hydrogen Bomb with a probable future development of Conversational AI ( Chatbots ).

Then I examined the petition and found that it contains vaguely similar mechanism for future regulation of AI , as proposed by me in " Parekh's Law of Chatbots " .

Please tabulate these parallel developments ( WMD and AI ) and comment on my proposal's feasibility

ChatGPT replied :

It is interesting to draw a parallel between the development of WMDs (Weapons of Mass Destruction) and the development of AI, specifically chatbots.

In the past, the development of WMDs such as the Atom/Hydrogen bomb was not regulated, leading to significant risks for humanity. Similarly, the development of AI, especially chatbots, is rapidly advancing without a regulatory framework, and some experts warn about its potential risks.

The Future of Life Institute, backed by Elon Musk, Steve Wozniak, and DeepMind engineers, has recently called for a pause in developing advanced AIs until a regulatory framework is established. OpenAI founder Sam Altman and Microsoft founder Bill Gates have also expressed concerns about AI's risks.

The call for a pause in AI development is similar to Parekh's Law of Chatbots, which proposes that chatbots should be regulated to prevent harm to humans.

The law states that chatbots should be designed with human safety in mind, and their development and deployment should be regulated by an international body.

The comparison between the development of WMDs and AI is intriguing, as both pose significant risks to humanity if not regulated appropriately.

It is crucial to have a regulatory framework to ensure that AI is developed and used safely.

Parekh's Law of Chatbots is a step in the right direction, and it is feasible to implement such regulation as long as all stakeholders, including AI developers, governments, and the public, work together to achieve this goal.

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

Belgian woman blames ChatGPT-like chatbot ELIZA for her husband’s suicide

-------------------------------------------------------------------------------------------------------------------

Added on 05 April 2023 :

Assess impact of AI tech: IT honchos

Monday, 27 March 2023

Salute, Sam Altman

Yesterday, for over 2 hours, I struggled to collect from various Government websites, details about Ayushman Card scheme , in order to enrol my domestic helpers

I discovered that unless their “ existence “ was recorded in Govt records during 2011 Census , they cannot be eligible for Ayushman Card

They would need to visit the nearest e-Seva Kendra or a Govt Hospital and carry with them , following documents :

Ø Aadhar Card

Ø PAN Card

Ø Ration Card

Ø Voter ID ( - I discovered, my domestic helpers do not have these )

During the process, I discovered that there is another similar scheme, offering to poor families, an ABHA card

Fortunately , I could get my domestic helpers to register online and obtain ABHA cards !

This made me think :

Ø Could Government find a way to SIMPLIFY the process of getting an Ayushman Card , for these poor people with no clue ?

Eg;

Authorising any doctor to examine / validate, just the Aadhar card of a

person / enter contact details into the relevant Govt website and

recommend issue of Ayushman Card

Ø Could Government release advertisements in all language news-papers,

tabulating the highlights of both the Card Schemes ?

So , I turned to ChatGPT and asked following question :

It seems Govt is considering Ayushman V 2.0, as per following report. Would it be possible for you to add a column to the right of the TABULATION you prepared above , give it a title " Ayushman 2.0 proposal - 27 Feb 2023 " and insert into that column, highlights from following news report ?

> https://economictimes.indiatimes.com/news/economy/policy/ayushman-2-0-in-works-for-400-million-mid-income-citizens/articleshow/99042601.cms?from=mdr Thank you for providing more information.

Based on the article you shared, it appears that the Indian government is considering a new version of the Ayushman Bharat program, called Ayushman 2.0, which would provide health insurance coverage to 400 million middle-income citizens.

The original Ayushman Bharat program, launched in 2018, is a government-funded health insurance scheme that provides coverage to over 100 million vulnerable families in India.

The proposed Ayushman 2.0 program would expand the scope of the original program to include middle-income citizens who may not qualify for the current scheme but are still at risk of high healthcare costs.

The specific details of the Ayushman 2.0 program are not yet available, as the government is still in the process of finalizing the scheme.

However, the program is expected to focus on providing coverage for outpatient services and diagnostic tests, which are not currently covered by the original Ayushman Bharat program.

Overall, the goal of Ayushman 2.0 is to improve healthcare access and affordability for a larger segment of the Indian population.

ChatGPT took 10 seconds to give following reply :

Criteria	AYUSHMAN Card	ABHA Card	Ayushman 2.0 Proposal - 27 Feb 2023
Purpose	Provide healthcare benefits to economically weaker sections and deprived rural families	Improve healthcare access for senior citizens in the country	Extend coverage to middle-income citizens
Eligibility criteria	- All families listed in SECC 2011 Data <br> - Families with no male member between 16-59 years <br> - Families with no adult members between 16-59 years <br> - SC/ST households <br> - Families living in one-room houses or no proper walls <br> - Destitute/ beggars/ manual scavenger families/ primitive tribal groups <br> - Families with at least one physically challenged member <br> - Landless households deriving a major part of their income from manual casual labour	- Citizens above the age of 60 years <br> - Those who are not covered under any other health insurance scheme	Middle-income citizens who do not qualify for current scheme
Enrollment Process	- Registration of eligible beneficiaries <br> - Issuance of e-cards to the eligible families <br> - Verification of beneficiaries through Aadhaar authentication, biometric identification or other documents <br> - After verification, the beneficiary can avail cashless treatment in any of the empanelled hospitals	- Eligible beneficiaries can apply for the card online or at the enrolment centres set up by the state government <br> - Verification of the applicant's age, identity and residence <br> - After verification, the beneficiary can avail cashless treatment in any of the empanelled hospitals	To be determined by the goernment
Benefits	- Free treatment for 1350 medical procedures across various specialties in government and empanelled private hospitals <br> - Pre and post-hospitalization expenses covered <br> - Transport allowances <br> - Cashless treatment	- Cover for critical illnesses <br> - Cashless treatment in government and private hospitals <br> - No medical test required for enrollment <br> - Pre and post-hospitalization expenses covered	Coverage for outpatient services and diagnostic tests
Insurance Coverage	Up to INR 5 lakhs per family per year	Up to INR 5 lakhs per family per year	To be determined by the government
Implementation Agency	National Health Authority (NHA)	State Governments	To be determined by the government

Note: INR stands for Indian Rupee, and 1 lakh is equal to 100,000.

Dear Shri Mandaviyaji

( Health Minister – Central Government )

I urge to publish the above-displayed TABULATION in all news papers – as also consider simplifying the process

With regards,

Hemen Parekh

www.hemenparekh.ai / 28 Mar 2023

( PS : My error : date in tabulation – last column - should be “ 27 March “ – not Feb )