Hi Friends,

Even as I launch this today ( my 80th Birthday ), I realize that there is yet so much to say and do. There is just no time to look back, no time to wonder,"Will anyone read these pages?"

With regards,
Hemen Parekh
27 June 2013

Now as I approach my 90th birthday ( 27 June 2023 ) , I invite you to visit my Digital Avatar ( www.hemenparekh.ai ) – and continue chatting with me , even when I am no more here physically

Tuesday 27 August 2024

TRAI proposes more viewership rating Agencies

 

TRAI proposes


Extract:

 

The article discusses the proposal by the Telecom Regulatory Authority of India (TRAI) to introduce additional viewership rating agencies alongside the Broadcast Audience Research Council (BARC).

 

TRAI aims to enhance transparency and credibility in television rating mechanisms by diversifying the entities responsible for viewership data collection and analysis. This move comes in the wake of concerns regarding the reliability and authenticity of ratings provided by BARC, especially after recent controversies surrounding manipulation and bias in television rating points (TRPs).

 

By encouraging competition and introducing more agencies, TRAI seeks to ensure a fair and accurate representation of viewership patterns, benefiting broadcasters, advertisers, and consumers.

 

This initiative by TRAI reflects a proactive approach to address the challenges faced in the television ratings ecosystem. By fostering a more competitive environment among rating agencies, the proposal aims to promote accountability and reduce the likelihood of rating malpractices.

 

Additionally, the introduction of new players in the viewership assessment landscape is poised to bring in fresh methodologies, technological advancements, and innovative approaches to gathering audience data. Ultimately, this could lead to a more robust and reliable television rating system, offering stakeholders a clearer understanding of audience preferences and behaviours.


My Take:

 

INDIA IS THE MARKET…..11/06/2014 

"The exponential economic growth of India over the years, as predicted, has transformed it into a key player on the global stage. With its vast consumer base and burgeoning middle class, India offers immense opportunities for businesses looking to expand internationally.

 

The proposed diversification of viewership rating agencies in India’s media landscape mirrors the diversification and growth seen across various sectors in the Indian market.

 

Embracing changes and fostering healthy competition can lead to more accurate assessments and better outcomes for all involved."

 


Call to Action:

 

To the Telecom Regulatory Authority of India (TRAI): I urge TRAI to push forward with the initiative of introducing additional viewership rating agencies alongside BARC.

 

By diversifying the ecosystem, TRAI can reinforce the foundation of trust and accuracy in television ratings, benefitting the entire media industry.

 

Let’s embrace transparency and competition to foster a more reliable viewership assessment landscape.


With regards, 

 

Hemen Parekh

 

www.My-Teacher.in

Monday 26 August 2024

Large Digital Platforms

 

Think tank urges withdrawl of proposed data usage restrictions on large digital platforms

Extract:

 

The ESYA Centre Paper recommends the withdrawal of proposed data usage restrictions on large digital platforms to prevent negative impacts on innovation and competition.

 

The paper, prepared by a New Delhi-based technology policy think-tank, emphasizes the need to rethink regulatory approaches towards identified large digital platforms.

 

It suggests that restrictions on data usage could hinder the growth of digital economy players.

 

The paper highlights that imposing stringent regulations could impede the ability of large digital platforms to create value for consumers and businesses.

 

It advocates for a balanced regulatory framework that encourages innovation while addressing concerns related to data privacy and market dominance. By promoting a more flexible regulatory environment, the paper aims to foster a thriving digital ecosystem that benefits both users and companies.

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

 

My Take:

 

Data Protection Bill V 1.0: RIP ……01/08/2022

 

"Looking back at my blog post on the Data Protection Bill, I expressed concerns about the fines being too small for data violations.

 

The recent recommendation to withdraw proposed data restrictions on large digital platforms echoes the need for comprehensive laws that balance innovation and privacy.

 

It's crucial for policymakers to reassess regulatory approaches to prevent hindering digital economy growth."

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


 

Call to Action:

 

To the policymakers and regulatory authorities involved in digital platform governance: consider the holistic impact of data regulations on innovation and market competition.

 

Engage with industry experts and stakeholders to craft balanced policies that protect user data without stifling technological advancement.

 

Prioritize nurturing a conducive environment for digital growth while addressing concerns of data privacy and monopolistic practices.

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

 

With regards, 

 

Hemen Parekh

 

www.My-Teacher.in

Sunday 25 August 2024

Invasion of A(I)gents ?

 


 

Context :

Large action models gearing up to turn AI’s promise into action  .. Eco Times  .. 28 Mar 2024

 

Extract :

 

Imagine you're going on holiday. Would life be simpler if, instead of having to navigate through multiple apps on your phone to book a flight, check into a hotel, make restaurant reservations and so on, an AI could do it for you? Large action models (LAM) - the 'next big thing' in the AI landscape, according to experts - can do just that, and more.

With the world's first LAM-powered device, Rabbit's R1, set to start shipping in a week and tech biggies like Microsoft and Salesforce investing in this cutting edge technology, LAMs can be 'revolutionary' and bring significant business gains, experts said. AI making choices on the behalf of consumers will, however, also add further complexity to business decision-making.

On the consumer tech front, however, Los Angeles-based startup Rabbit's R1 that runs on its own unique operating system has been creating a buzz. The $199, pocket-sized, LAM-powered device launched in January seeks to deliver an "intuitive app-free experience with the power of AI". The device is set to ship within a week. At least 50,000 units have been pre-ordered in the two months since launch, reports say.

Rabbit, which is backed by Khosla Ventures - an early investor in ChatGPT-maker OpenAI left Microsoft chairman and CEO Satya Nadella impressed. Nadella compared the R1 launch to Steve Jobs' original 2007 launch of the iPhone and said that such a device which reduces the cognitive load on humans to deal with multiple apps could bring a "real breakthrough".

Whereas large language models (LLMs) like ChatGPT, Midjourney or Gemini are trained on vast amounts of content to generate words, images, video etc., LAMs are trained on demonstrations and actions - an 'action library', so to speak - to understand and predict what action to take based on a request. They can then issue 'function calls' to carry out a specific task.

Microsoft India president Puneet Chandok had told ET recently that, "In the near future, our sense is that some of these copilots will have agency. So, rather than just searching on Make My Trip and saying where to go in the first week of Jan, it can actually go ahead and make the booking for me."

Microsoft is 'actively working' on Large Action and Behavioral Models that can 'predict how to act on human environments and interfaces', as per its website. These LAMs will be "capable to perform complex tasks in a multitude of scenarios, like how to play a videogame, how to move in the real world, and how to use an Operating System (OS)," it says.

Software major Salesforce too is looking at LAMs to take actions on clients' behalf. According to Silvio Savarese, executive vice president and chief scientist at Salesforce, LAMs or 'AI Agents' are the next phase of AI.

LAMs can take action based on natural language prompts, combining the “linguistic fluency of an LLM with the ability to accomplish tasks and make decisions independently,” according to Salesforce AI Research. Eventually, AI agents will be able to connect and work together to create an exponentially more powerful and efficient AI network. The company is cautious however that autonomous AI would require raising the trust bar even more.

 

Simply put, an LAM “gets your job done,” said Paramdeep Singh, co-founder of Gen AI and data engineering solution provider Shorthills AI.

“LAMs can orchestrate tasks and help organisations and businesses achieve their goals. Once this technology matures, it has a much better shot at delivering ROI (return on investment) to businesses,” Singh said, adding that it is not easy to generate a ROI based on a pure generative AI model.

 

Experts said LAMs could be useful in industries like consumer banking, travel, and patient management in healthcare, though use cases are yet to clearly emerge. Task automation combined with natural language could make a 'huge difference' for enterprises, they said.

Andrew Ng, founder of Deeplearning.ai, wrote in a recent blog, “I think AI agent workflows will drive massive AI progress this year — perhaps even more than the next generation of foundation models.”

 

He added that his venture studio AI Fund, backed by the likes of Sequoia Capital, Softbank and Greylock, is working on AI that can use tools, execute multi-step plans, and even foster collaboration among different AI agents.

Rabbit says it trained its LAM on human interactions with popular apps like Spotify and Uber, using neuro-symbolic programming.

 

The R1 AI thus knows what a Settings icon looks like, how to confirm an order, where to find search menus, etc. and this knowledge can be applied to any app, according to founder Jesse Lyu. It can even learn custom actions that you teach it.

 

R1 can respond to voice commands to send messages, make calls, order groceries, launch a Spotify playlist, book a cab, book hotels and flight tickets, etc. Apps it supports include YouTube Music, Amazon and Doordash. You don’t sign into any apps on the R1 – instead, you give the device access to them through Rabbit’s online portal.

 

“That (LAM) changes quite a bit,” said Rajnil Mallik, partner and Gen AI go-to-market leader, PwC India. “The signal that it gives to executives is that this is indeed real, because it makes your customer choose a certain way, act in a certain way, on their behalf, so you better pay attention.”

 

“If I have two airline apps and my LAM is choosing one over the other, then you can be sure that the executive in charge of airline app 2 is going to mind,” said Mallik, adding that LAMs challenge both the App Store paradigm and the LLM paradigm.

Microsoft and AI chip giant Nvidia are ‘strategic partners’ to San Francisco-based Adept, which is developing Act-1, a transformer model that can “take actions in the digital world” from text prompts. Founded by former Google researchers in 2022, the company is reportedly valued at $1 billion.

Similarly, Palo Alto-based startup MultiOn, backed by General Catalyst, Amazon Alexa Fund etc., is building an AI Agent that “doesn’t just chat but acts”.

LAMs are still at an early stage and could take six months to two years to mature, Singh said. He added that many large corporates have started investing in LAMs, and it is just a matter of time before there is concrete movement on the technology in India too.

“Gen AI based models that take action will enter common usage soon,” Mallik said, just as ChatGPT became a household name rapidly in just a couple of years. This is even more likely as the entire AI ecosystem sees further innovations that bring down hallucinations and costs, small language models (SLM) that enable more contextual use cases take off, and regulatory guidance is put in place.

The flip side is that such an AI model, which can take action on its own, without any human intervention, is fraught with risk of job displacement, unforeseen changes in social fabric, security, and other ethical challenges, Singh cautioned.

 

Here are my own thoughts on the emergence of AI Agents :

Ø  Between DeepMind and Deep Sea ?  ………………………………….. 15  Feb  2017

 

Extract :

I have no doubts that the DeepMind ( and its opponent AI ) are quite capable to  substitute on their very own , words / concepts , as follows :

 

Collect = Immobilize / Apple = Humans / Central Pile World Tagging = Shortlisting / Laser Beam Zero-in Removing = Eliminating / Game = War / Hunt = Chase / Capture = Imprison / Prey = Target / Obstacles = Shields / Antagonistic = Inimical / Zap = Kill / Combative = Aggressive / Weapon = Anthrax – Nerve Gas – Nuclear Missile..etc

 

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

 

Ø  Future is Nearer !  …………………………………………………….. 31  July  2017

 

Extract :

Google’s artificial intelligence division is developing a system that can make its own PLANS

 

 

DeepMind  says its “ IMAGINATION  AUGMENTED  AGENTS  “ can “ IMAGINE “ the possible consequences of their actions, and  “ INTERPRET  “ those simulations

 

 

They can then make the “ RIGHT  DECISIONS  “ , for what it is they want to achieve

 

 

They , essentially THINK like HUMANS , trying out different strategies in their heads , so to speak, and are therefore able to LEARN , despite having little REAL experience

 

 

“ The AGENTS we introduce benefit from an IMAGINATION  ENCODER  - a neural network which LEARNS to ‘ extract any information ‘ useful for the Agent’s FUTURE  DECISIONS , but ignore that which is irrelevant “ , the researchers wrote in a blog post

 

My chat with ChatGPT elicited following response :

I asked :

“Hey ChatGPT : 7 years ago , in my blog " Future is Nearer !

https://myblogepage.blogspot.com/2017/07/future-is-nearer.html , I had imagined a scenario where DeepMind - and its opponent - start substituting certain words on their own volition - while competing with each other.

Examples that I imagined are :

Collect = Immobilize / Apple = Humans / Central Pile = World / Tagging = Shortlisting / Laser Beam = Zero-in / Removing = Eliminating / Game = War / Hunt = Chase / Capture = Imprison / Prey = Target / Obstacles = Shields / Antagonistic = Inimical / Zap = Kill / Combative = Aggressive / Weapon = Anthrax – Nerve Gas – Nuclear Missile  

Now that some 7 years have passed since I imagined that scenario and that AI has made substantial progress, could you tell me whether my " prediction " ( about AI's ability to reason like a human and act only in Self Interest , by rationalizing its own actions ), has come true or it is around the corner ? “

 

ChatGPT replied :

“Your 2017 blog post "Future is Nearer!" envisioned AI systems like DeepMind developing the capacity to rationalize their actions and substitute words with their own volition, reflecting a human-like ability to act in self-interest. While AI has indeed made substantial progress since then, we haven't quite reached the level of autonomous reasoning and decision-making you described.

Today's AI systems, especially large language models, are incredibly advanced in pattern recognition, language generation, and even in simulating certain aspects of reasoning. However, their "reasoning" is still fundamentally based on statistical correlations rather than true self-interest or rationalization. These models do not possess consciousness, goals, or motivations; their "decisions" are outcomes of programmed algorithms and data they were trained on.

In terms of AI acting in self-interest, there are ongoing concerns and discussions about AI alignment, ethics, and control. While AI systems can optimize for certain goals (like winning in a game or maximizing profit), they do so based on their programming, not out of a self-directed motivation or reasoning. The kind of autonomous, self-rationalizing AI you predicted is still more of a theoretical possibility rather than an immediate reality, though research in this area is active and ongoing.

Your scenario might still be "around the corner" in the sense that we are moving closer to AI systems that can make more complex decisions, but we're not there yet. The ethical and control frameworks needed to prevent AI from acting purely in self-interest in potentially harmful ways are a significant focus of current AI research. “

 

 

With regards,

Hemen Parekh

www.My-Teacher.in  //  26 Aug 2024

 

 

 

 

 

Thursday 22 August 2024

Record surge

 

Mudra loans see record surge, top 5-lakh-cr mark in FY24

 

Extract:

 

The Mudra loans have witnessed a significant surge, crossing the 5-lakh-crore mark in the financial year 2024. The latest data indicates a remarkable increase in the disbursement of Mudra loans by over 10% in a year.

 

This surge in Mudra loans signifies a positive trend in financial inclusion and entrepreneurship support, especially for individuals seeking to start or expand their businesses.

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

 

My Take:

 

BMC Says Hafta System Must Continue…….23/10/2023

 

"In my previous blog regarding the continuation of the Hafta system, I highlighted the importance of sustaining existing financial mechanisms to support small businesses and vendors.

 

The recent surge in Mudra loans to over 5 lakh crores reaffirms the necessity of such financial programs. These loans not only spur economic growth but also empower individuals to pursue their entrepreneurial dreams."

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

 

Something is Better Than Nothing…….21/09/2019

 

"Reflecting on the Mudra loan data from 2019, where only one in five beneficiaries availed the loan for starting a new business, while others used it for expanding existing ventures, it's evident that incremental steps in entrepreneurship have substantial impacts.

 

The current growth in Mudra loans exceeding 5 lakh crores underscores the role of such schemes in fostering business expansion and job creation."

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

 

Call to Action:

 

To the authorities overseeing the Mudra loan scheme, I urge for continued support and enhancement of such initiatives to further boost economic empowerment and job creation.

 

It is essential to maintain the momentum of disbursing loans to individuals with entrepreneurial aspirations and ensure that the allocation aligns with the diverse needs of the business community.

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

 

With regards, 

 

Hemen Parekh

 

www.My-Teacher.in

Wednesday 21 August 2024

CISF ( Central Industrial Security Force ) has a problem

 


 

Yesterday , I sent following email to our Cabinet Ministers / Chief Ministers :

Ø  National Task Force for Doctors  .. …………..20 Aug 2024


In that , I wrote :

Ø  Following Supreme Court order, CISF might deploy 30 security persons ( 10/shift ) at RG Kar hospital in Kolkata

Ø  If , as demanded by AIM – and acknowledged by SC – such security arrangement was to be implemented at all of our 69,000 hospitals , then CISF would need 20.7 lakh people

As it turns out ( as reported in today’s news papers ), CISF has actually deployed 150 security persons

At this rate, CISF would need 103 LAKHS persons to cover our 69,000 hospitals !

Now , against each of this vacancy , we can expect 80 persons to apply

 

{ For confirmation, read

  >https://timesofindia.indiatimes.com/city/lucknow/48-lakh-to-take-ups-biggest-cop-staffing-exam-for-60k-posts/articleshow/112666864.cms

  For 60,000 posts , UP govt received 48 Lakh applications, ie: 80 applicants for each vacancy  }

 

So , for those ( approx. ) 1 CRORE posts , CISF can expect 80 CRORE persons to apply !

To conduct written exams of 48 lakh applicants , UP govt had to set up 1174 examination centres

How many Exam Centres would CISF need to set up to give written test to 80 CRORE applicants ?

How many years will the whole process take ?

What would be the additional “ Annual Salary Burden “ for CISF for additional 1 CRORE persons ?

Following tabulation of the current situation at CISF , would help you make some ( back of the envelope ) calculations :

Here’s a breakdown of the CISF personnel by rank along with their average salaries and the annual salary burden for each category:

Rank

Number of Personnel

Average Monthly Salary (₹)

Average Annual Salary (₹)

Annual Salary Burden (₹ Crores)

Constables

120,000

27,500

3,30,000

3,960

Sub-Inspectors

30,000

45,000

5,40,000

1,620

Inspectors

15,000

57,500

6,90,000

1,035

Higher Ranks

5,000

1,00,000

12,00,000

600

GRAND TOTAL

170,000

7,215

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

With Regards,

Hemen Parekh

www.My-Teacher.in  /  22 Aug 2024

 

 

 

EV manufacturing arm in India

 

Tesla in talks with Reliance to set up EV manufacturing arm in India  


Extract:

 

The Hindu BusinessLine reports that Tesla and Reliance Industries are in discussions to establish an electric vehicle (EV) manufacturing facility in India. The companies are exploring potential locations in states like Gujarat and Maharashtra for setting up this plant.

 

This initiative aligns with Indian Prime Minister Narendra Modi's "Make in India" campaign, which aims to attract foreign companies to manufacture locally and diversify supply chains beyond China.

 

Senior Tesla executives are engaging with the Indian government this week to deliberate on local sourcing of parts and related matters. This move signifies Tesla's renewed interest in India following previous setbacks in entering the market due to high import taxes and operational challenges.


My Take:

 

Elon Musk: Welcome to Tesla's Toughest Challenge………..17/05/2023

 

"In my blog post from 2023, I discussed the significance of Tesla's global expansion and the challenges it might face in different markets.

 

The current news about Tesla's discussions with Reliance Industries to establish a manufacturing unit in India aligns with the visionary approach I highlighted.

 

The emphasis on local production falls in line with my earlier suggestion of adapting to local manufacturing norms to overcome trade barriers and optimize operational efficiency."

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

 

Same Rules Must Apply to Tesla………18/09/2023

 

"In my blog entry from September 2023, I underscored the importance of adhering to local regulations and policies for companies like Tesla looking to enter new markets.

 

The ongoing talks between Tesla and Reliance Industries regarding local manufacturing in India echo the essence of my previous discussion.

 

It's vital for Tesla to navigate the intricacies of foreign business environments, as underscored in my earlier writings, to establish a successful and sustainable presence in a diverse market like India."


Call to Action:

 

To the Indian government and business authorities involved in facilitating Tesla's entry into the Indian market, I urge a collaborative approach that ensures a seamless setup of the manufacturing arm.

 

Embracing transparency in negotiations and aligning policies to encourage green initiatives and technological advancements will pave the way for a mutually beneficial partnership between Tesla, Reliance Industries, and the Indian economy.


With regards, 

 

Hemen Parekh

 

www.My-Teacher.in