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

Monday, 6 March 2023

Freedom of Speech ? Or a “ License to Abuse ? “

 


 

 

Context :

Article 105 of Constitution: The limits to free speech in Parliament, and what Supreme Court has ruled

 

Extract :

Protesting against the expunction of parts of his speech on the motion of thanks on the President’s Address, Leader of Opposition in Rajya Sabha and Congress president Mallikarjun Kharge has argued that MPs have freedom of speech, and that he did not make any personal allegations in the House.

In his letter to Rajya Sabha Chairman Jagdeep Dhankhar on Thursday (February 9), Kharge cited Article 105 of the Constitution that deals with the privileges and powers of parliamentarians. What is the provision and how does it protect MPs?

 

What does Article 105 say?

Article 105 of the Constitution deals with “powers, privileges, etc of the Houses of Parliament and of the members and committees thereof”, and has four clauses. It reads:

 

“(1)

Subject to the provisions of this Constitution and to the rules and standing orders regulating the procedure of Parliament, there shall be freedom of speech in Parliament.

(2)

No member of Parliament shall be liable to any proceedings in any court in respect of any thing said or any vote given by him in Parliament or any committee thereof, and no person shall be so liable in respect of the publication by or under the authority of either House of Parliament of any report, paper, votes or proceedings.

(3)

In other respects, the powers, privileges and immunities of each House of Parliament, and of the members and the committees of each House, shall be such as may from time to time be defined by Parliament by law, and, until so defined, shall be those of that House and of its members and committees immediately before the coming into force of section 15 of the Constitution (Forty-fourth Amendment) Act, 1978.

(4)

The provisions of clauses (1), (2) and (3) shall apply in relation to persons who by virtue of this Constitution have the right to speak in, and otherwise to take part in the proceedings of, a House of Parliament or any committee thereof as they apply in relation to members of Parliament.”


Simply put, Members of Parliament are exempted from any legal action for any statement made or act done in the course of their duties.


For example, a defamation suit cannot be filed for a statement made in the House.


This immunity extends to certain non-members as well, such as the Attorney General for India or a Minister who may not be a member but speaks in the House. In cases where a Member oversteps or exceeds the contours of admissible free speech, the Speaker or the House itself will deal with it, as opposed to the court.

 

So are there absolutely no restrictions on this privilege?

There are some, indeed. For example Article 121 of the Constitution prohibits any discussion in Parliament regarding the “conduct of any Judge of the Supreme Court or of a High Court in the discharge of his duties except upon a motion for presenting an address to the President praying for the removal of the Judge..”.

 

Where did the idea of this privilege of Parliament originate?

The Government of India Act, 1935 first brought this provision to India, with references to the powers and privileges enjoyed by the House of Commons in Britain. An initial draft of the Constitution too contained the reference to the House of Commons, but it was subsequently dropped.

However, unlike India where the Constitution is paramount, Britain follows Parliamentary supremacy. The privileges of the House of Commons is based in common law, developed over centuries through precedents.

In the 17th-century case ‘R vs Elliot, Holles and Valentine’, Sir John Elliot, a member of the House of Commons was arrested for seditious words spoken in a debate and for violence against the Speaker. However, the House of Lords provided immunity to Sir John, saying that words spoken in Parliament should only be judged therein.

This privilege has also been enshrined in the Bill of Rights 1689, by which the Parliament of England definitively established the principle of a constitutional monarchy.

In the 1884 case of ‘Bradlaugh v. Gosset’, then Chief Justice Lord Coleridge of the House of Lords observed: “What is said or done within the walls of Parliament cannot be inquired into in a court of law.”

 

And what have courts in India ruled?

* In the 1970 ruling in ‘Tej Kiran Jain v N Sanjiva Reddy’, the Supreme Court dismissed a plea for damages filed by the followers of the Puri Shankaracharya against parliamentarians.

The judgment recalled that “in March 1969, a World Hindu Religious Conference was held at Patna. The Shankaracharya took part in it and is reported to have observed that untouchability was in harmony with the tenets of Hinduism and that no law could stand in its way, and to have walked out when the National Anthem was played.”

 

The petitioners claimed that when the issue was debated in Parliament, uncharitable remarks were made against the seer. The petitioners argued that the MPs’ immunity “was against an alleged irregularity of procedure but not against an illegality”.

 

However, the SC ruled that “the word “ anything ” in Article 105 is of the widest import and is equivalent to ‘everything’.”

 

* Almost two decades later, in 1998, the SC in the case of ‘P V Narasimha Rao vs. State’ answered two questions on parliamentary privilege, broadly relating to questions of corruption.


In 1993, Narasimha Rao was Prime Minister of a minority government at the Centre. When a vote of no-confidence was called by members of the opposition against the government, some factions of the ruling party paid Jharkhand Mukti Morcha (JMM) members to vote against the motion. The motion was defeated in the House, with 251 members supporting it and 265 members against it.

Two questions came before the Supreme Court.


One, whether MPs could claim immunity from prosecution before a criminal court on charges of bribery related to parliamentary proceedings, under Articles 105(1) and 105(2).

 

Two, whether an MP is a “public servant” under the Prevention of Corruption Act, 1988.

 

A five-judge Bench of the apex court ruled that the ordinary law would not apply to the acceptance of a bribe by an MP in case of parliamentary proceedings.

 

“Broadly interpreted, as we think it should be, Article 105(2) protects a Member of Parliament against proceedings in court that relate to, or concern, or have a connection or nexus with anything said, or a vote given, by him in Parliament,” the court said, giving a wider ambit to the protection accorded under Article 105(2).

 

The Court rationalised this by saying it will “enable members to participate fearlessly in Parliamentary debates” and that these members need the wider protection of immunity against all civil and criminal proceedings that bear a nexus to their speech or vote.

 

MY  TAKE  :

 

Ø  Freedom of Speech ?  ………….  13 Nov 2013

 

Extract :


Today , on Nehru's birthday , I am reminded of his following speeches :

 

 >    Our tryst with destiny

 

 >    A light has gone out of our lives

  

Then there were other memorable speeches in the distant past, viz:

 

 >    Mahatma Gandhi      (  Quit India  )

  

>    Martin Luther King    (  I have a dream  )

 

 >    Abraham Lincoln       (  Of the people / by the people / for the people  )

 

 >    Winston Churchill     (  Never have so many owed so much to so few  )

 

 >    Brutus                     (  but Caesar is an honorable man  )

 

  

Then I end up comparing some " famous " recent speeches , viz:,

  

>    Sonia Gandhi           (  Maut ka Saudaagar  )

 

>    Narendra Modi         ( Khooni  Panjaa  )

 

>    Rahul Gandhi           (  ISI  )

 

>    Kapil Sibal                (  No loss in 2G scam  )

 

>    Manish Tewari           ( Anna is most corrupt  )

 

>    Ranjeet Sinha            (  Enjoy rape  )



>    Naresh Agarwal         (
a tea-vendor cannot become PM  / even Madari

                                        collects crowds  )

 

 

 

No doubt , amongst the living politicians , " Freedom of Speech " has totally different connotations  !

 

 For them , apparently , it means,

  

License to Kill ( - if words can kill  !  ) "

 

Obviously , Gandhian Anna Hazare  is pained

 

In his TV interview with Rajat Sharma yesterday , he expressed his anguish at the

lowly depths to which , political mud-slinging has descended during current

election campaign

 

Whether he / she is a leader of any political party , all politicians are talking the

same language , the language of ,

 

PHP   =   Power Hungry Politicians

  

Who cares for ,

  

C = Civility / Code of Conduct / Courtesy  ?

 

I  miss T N Sheshan   !

 

I cannot escape the feeling that , in past 10 years since I wrote the above blog ,

mud-slinging between our politicians has gone from “ Bad to Worse 


By the time voting time for next General Election arrives ( next March ? ), I

believe , it will go from “ Worse to Worst


If things keep getting worse at this rate, it may be time to forget about applying :


Parekh’s Law of Chatbots ,


-       to “ Artificial Intelligence “ ,


and consider applying it ,


-        to “ Power-Hungry Human Arrogance



 

With Regards,

Hemen Parekh

www.hemenparekh.ai  /  06 Mar 2023

Sunday, 5 March 2023

Now Assurance : Next , Obligation ?

 


 

Context :

Apple okays ChatGPT-powered app after assurance of content moderation: WSJ  

  

Extract :

Apple has approved an email-app update after initially scrutinising whether a feature in the software that uses language tools powered by artificial intelligence could generate inappropriate content for children, The Wall Street Journal said.

The app, BlueMail, was approved following assurances from its developer that it features content moderation, according to Ben Volach, co-founder of the app-maker, Blix.

The Wall Street Journal reported on Thursday that the update, which included a new feature powered by language chatbot ChatGPT, was held up due to Apple’s request that the app add content moderation or be restricted to ages 17 and older. The app was previously available for ages 4 and older.

Blix told Apple its update includes content moderation and suggested that the company should make public any new policies about the use of ChatGPT or other similar AI systems in apps, according to WSJ. The BlueMail update was approved without changes on Thursday evening. The app is still available for users aged 4 and older.

WSJ said Apple didn’t respond to requests for comment.

BlueMail’s new feature uses OpenAI’s ChatGPT, an artificial-intelligence system capable of answering questions or writing short essays, to help automate the writing of emails using the contents of prior emails and calendar events, according to WSJ.

The news of Apple’s initial rejection of BlueMail’s ChatGPT feature highlighted the growing concerns around new uses of language-generating AI tools, according to WSJ, adding that ChatGPT allows users to converse with an AI that appears humanlike, but early testing has shown the AI producing incorrect information as well as strange and sometimes hostile responses. (ANI)

 

How are we going to stop machine learning assistants from spreading fake news?        

Extract :

A race is underway to incorporate machine learning into search engines so they can answer queries with a paragraph as well as a list of links: the pioneer, the still relatively unknown You.com, was joined by Bing thanks to Microsoft’s agreement with Open.ai, while Google is experimenting with Bard. And on Friday, Brave Search announced an AI summarization feature that isn’t based on ChatGPT.

Meanwhile, ChatGPT says it has overcome some initial problems, as well as providing easier access from other countries such as Spain, which, together with its integration in more and more search engines, will likely see even more use around the world.

Noting this possible change in the usage model, The Atlantic raises an interesting question: what happens to the results that search engines offer about a person and that are possibly false, misleading or malicious, defamatory or based on conspiracy theories, when those results are included in a well-written paragraph.

Could generative assistants trained with material gleaned from the internet become the perfect allies for conspiracy theories or fake news?

Hopefully, most of us will continue to use our critical faculties to question the results of searches, but for whatever reasons, others won’t, and by responding to a conversational dynamic in which previous interactions are introduced as part of the context, they may contribute to the creation of filter bubbles and, in general, to the spread of conspiracy theories and fake news.

In short, once again we talking about the interaction between critical thinking and conversational assistants, which in general try to apply a certain caution and, when asked to criticize somebody, tend to respond with formulas such as:

“As a language model, my programming prevents me from providing false or defamatory information about people. To criticize someone in a mean-spirited or baseless way is inappropriate and unfair.”

But by injecting ideas via prompt into a conversation, it is relatively easy to get these assistants to criticize or construct negative arguments based on anything they find on the web that they give credibility to, which means the documentation they use is going to have to pass some kind of quality control to the documents these assistants are trained on.

This is surely already in place, but runs the risk of editorialization, even charges of censorship: Elon Musk has already accuse OpenAI’s ChatGPT, a company he helped found, of having a liberal bias, and says he wants to recruit people to develop an alternative, less “woke” model.

Anyone who lets a search assistant do their thinking for them deserves what they get. But in a scenario of increasingly common use of such technology, we are faced with a problem that may end up being quite complex.

We’ll see what happens as they evolve.

 

My  Take  :

 

Thank You, Satya Nadella,

satyan@microsoft.com

 

By getting from Blix , the developer of  BlueMail , an assurance for incorporating in the App , a CONTENT  MODERATION feature

While agreeing with your request, Blix has suggested you to “ Spell Out “ your ( Apple’s ) POLICY about the “use of ChatGPT or other similar AI systems in apps


A very reasonable suggestion

 

But a POLICY adopted by Apple alone, is not good enough


What is urgently needed is an INDUSTRY-WIDE policy


I urge you to initiate a DEBATE by circulating among the key INDUSTRY PLAYERS,

my following suggestion :

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

 

Extract :

( A )

#   Answers being delivered by AI Chatbot must not be “ Mis-informative /

     Malicious / Slanderous / Fictitious / Dangerous / Provocative / Abusive /

     Arrogant / Instigating / Insulting / Denigrating humans etc

     

( B )

#  A Chatbot must incorporate some kind of  “ Human Feedback / Rating 

    mechanism for evaluating those answers 

    This human feedback loop shall be used by the AI software for training the

    Chatbot so as to improve the quality of its future answers to comply with the

    requirements listed under ( A )

    

    

( C )

#  Every Chatbot must incorporate some built-in “ Controls “ to prevent the “

    generation “ of such offensive answers AND to prevent further “

    distribution/propagation/forwarding “ if control fails to stop “ generation “

  

 

 ( D )

#   A Chatbot must not start a chat with a human on its own – except to say, “

     How can I help you ? “

 

( E )

#   Under no circumstance , a Chatbot shall start chatting with another Chatbot or

     start chatting with itself ( Soliloquy ) , by assuming some kind of “ Split

     Personality “

 

     

( F )

#   In a normal course, a Chatbot shall wait for a human to initiate a chat and

     then respond

 

( G )

#   If a Chatbot determines that its answer ( to a question posed by a human ) is

     likely to generate an answer  which may violate RULE ( A ) , then it shall not

     answer at all ( politely refusing to answer )

     

 

( H )

#   A chatbot found to be violating any of the above-mentioned RULES, shall SELF

     DESTRUCT

 

With Regards,

Hemen Parekh

www.hemenparekh.ai  /  06  March  2023

 

Related Readings :

Ø  Chatbot Regulation Seems Inevitable  … ……………….. 27 Feb 2023

 

Ø  My “ Law of Chatbots “ – Vindicated … …………………… 02 Mar 2023

 

 

 

 

Saturday, 4 March 2023

Shri Rahul Gandhi’s cry : PEGASUS

 


 

Context :

‘I had Pegasus on my phone,’ says Rahul Gandhi at Cambridge;    /   Indian Express  /  03 Mar 2023

 

Extract :


Congress leader Rahul Gandhi, during his recent lecture at Cambridge University, alleged that the Israeli spyware Pegasus had been used to snoop on him and several other politicians.


He alleged that he had been warned by intelligence officers to be “careful” while speaking on the phone as his calls were being recorded.


I myself had Pegasus on my phone.


Large number of politicians have Pegasus on their phones. I’ve been called by Intelligence officers who say please be careful of what you say on your phone as we are recording the stuff,” the Congress leader had said, according to news agency ANI.

 

 

Dear Rahulji ,


office@rahulgandhi.in


Rahul.gandhi@sansad.nic.in

 

I am surprised that no one from your audience asked you the following question which I asked ChatGPT  :

 

Question :

 

How does Mobile based malware " zero click remote exploit " work ? Would the owner of the infected mobile, ever get to know what data about him , is being collected without his knowledge ? Which companies provide such " INVISIBLE " malware ?

 

Answer :

 

 "Zero-click remote exploit" is a type of mobile-based malware that can infect a device without any action from

 the user, such as clicking on a link or downloading an attachment. These exploits take advantage of

 vulnerabilities in the device's operating system or applications to gain control of the device.

Once a device is infected with this type of malware, the attacker can gain access to sensitive information, such

 as personal data, login credentials, and financial information.

They can also remotely control the device, such

 as turning on the camera or microphone, and stealing sensitive information without the user's knowledge.

It is difficult for the owner of an infected mobile to know what data is being collected without their knowledge,

 as these types of malware are designed to operate invisibly and stealthily.

Some signs of a potential malware

 infection may include decreased battery life, unusual data usage, and the device running slower than usual.

As for the companies that provide such "invisible" malware, it is illegal to create or distribute malware, so no

 legitimate company would offer such products. Criminal organizations and individuals can create and distribute

 malware, either to steal information or to sell access to infected devices to other criminals.

It's important to keep your mobile devices updated with the latest security patches and avoid downloading apps from untrusted sources to minimize the risk of being infected with mobile-based malware. If you suspect that your device has been infected, you should immediately disconnect it from the internet and seek assistance from a cybersecurity professional.

Top of Form

 

With regards,

Hemen Parekh

www.hemenparekh.ai   /  05 March 2023

Related Readings :

Ø  Balancing : National Security vs Personal Privacy……………………   19 July 2021

Ø  Pegasus : Give it to a Surgeon …………………………………………………..  20 July 2021

Ø  Will mother Medusa replace son Pegasus ?  ………………………….     29 July 2021

Ø  Dear Supreme : How about asking Pegasus to file an Affidavit ?  15 Sept 2021

Ø   Pegasus Committee : Terms of Reference  …………………………..      26 Sept 2021

Ø  Supremely Satisfactory  ……………………………………………………………….  27 Oct 2021

Ø  Microsoft says : User is the Content  …………………………………………    30 Jan 2022

Ø  Surveillance : make it a “ Compromise Issue?  ………………………… 28 Mar 2022

 

 

 

 

CC:

Shri Ashwini Vaishnawji ……..( av.odisha@sansad.nic.in )

Shri Shri Kiren Rijiju ……  …..( kiren.rijiju@sansad.nic.in )

Shri Anurag Singh Thakur …( anuragthakur.mp@sansad.nic.in )

Dr. Jitendra Singh ……………..( drjitendras@gmail.com )