Sure,
- but whereas EU Law of AI may not get every AI developer
on the board for next 2 years ,
- BIG ( and small ) TECH can reach a consensus on a
“ self regulatory Law of Chatbots “ , within 2 months !
With regards,
Hemen Parekh
www.hemenparekh.ai / hcp@RecruitGuru.com
=============================================
Context :
EU Likely to Reach
Political Agreement on AI Law This Year, Says Tech Regulator Chief Vestager
( Gadget360
/ 01 May 2023 )
Extract :
The European Union is
likely to reach a political agreement this year that will pave the way for the
world's first major artificial intelligence (AI) law, the
bloc's tech regulation chief Margrethe Vestager said on Sunday.
This follows a preliminary
deal reached on Thursday by members of the European Parliament to push through
the draft of the EU's Artificial Intelligence Act to a vote by a committee of
lawmakers on May 11. Parliament will then thrash out the bill's final details
with EU member states and the European Commission before it becomes law.
At a press conference after a
Group of Seven digital ministers' meeting in Takasaki, Japan, Vestager said the
EU AI Act was "pro-innovation" since it seeks to mitigate the risks
of societal damage from emerging technologies.
Regulators around the world
have been trying to find a balance where governments could develop
"guardrails" on emerging artificial intelligence technology without
stifling innovation.
"The reason why we have
these guardrails for high-risk use cases is that cleaning up … after a misuse
by AI would be so much more expensive and damaging than the use case of AI in
itself," Vestager said.
While the EU AI Act is
expected to be passed by this year, lawyers have said it will take a few years
for it to be enforced. But Vestager said businesses could start considering the
implication of the new legislation.
"There was no reason to
hesitate and to wait for the legislation to be passed to accelerate the
necessary discussions to provide the changes in all the systems where AI will
have an enormous influence," she said in the interview.
While research on AI has been
going on for years, the sudden popularity of generative AI applications such as
OpenAI'S ChatGPT and Midjourney have led to a
scramble by lawmakers to find ways to regulate any uncontrolled growth.
An organisation backed
by Elon Musk and European lawmakers involved
in drafting the EU AI Act are among those to have called for world leaders to
collaborate to find ways to stop advanced AI from creating disruptions.
Digital ministers of the G7
advanced nations on Sunday also agreed to adopt "risk-based" regulation
on AI, among the first steps that could lead to global agreements on how to
regulate AI.
"Now when everyone has
AI at their fingertips ... there's a need for us to show the political
leadership to make sure that one can safely use AI and gain all the amazing
possibilities of improvement in productivity and better services,"
Vestager said in an interview with Reuters.
My poser to ChatBot :
Many
thanks for this quick comparison and contrast . I would appreciate if you could
reformat your views , ( comparing the features of the two ), in a TABULATED
format , for quick and easy grasp
Chatbot replied :
Certainly, here is a tabulated format
for the comparison and contrast of the proposed EU law to regulate AI and the
proposed "Law
of Chatbots":
|
Features |
Proposed EU law to regulate AI |
Proposed "Law
of Chatbots" |
|
Purpose |
Regulate
AI technologies to mitigate societal risks |
Regulate
chatbots to ensure ethical and fair use |
|
Scope |
Covers
all AI technologies, with a focus on high-risk applications |
Specifically
targets chatbot
technology |
|
Enforcement |
Will
take a few years to be enforced |
Not
specified |
|
Timeframe |
Expected
to be passed by this year |
Not
specified |
|
Political
support |
Backed
by EU tech regulation chief Margrethe Vestager and members of the European
Parliament |
Not
specified |
|
Innovation
support |
Considered
"pro-innovation" |
Not
specified |
|
Risk-based
approach |
Utilizes
"guardrails" for high-risk applications |
Not
specified |
|
Global
collaboration |
Calls
for world leaders to collaborate on AI regulation |
Not
specified |
|
Stakeholders |
EU
member states, European Commission, businesses |
Chatbot
developers, businesses using chatbots, consumers |
|
Potential
impact |
Could
pave the way for global agreements on AI regulation |
Could
improve the ethics and fairness of chatbot technology |
I hope this format helps you in
comparing and contrasting the two proposed laws.
Related Readings :
AI
Chatbots Have Been Used to Create Dozens of News Content Farms ……………. Bloomberg / 01
May 2023
Extract :
The news-rating group NewsGuard has found dozens of
news websites generated by AI chatbots proliferating online, according
to a report published
Monday, raising questions about how the technology may supercharge
established fraud
techniques.
But none disclose they’re populated using AI chatbots such as OpenAI Inc.’s ChatGPT and
potentially Alphabet Inc.’s Google Bard, which can
generate detailed text based on simple user prompts.
The majority of the sites appear to be content farms — low-quality websites run by anonymous sources that
churn-out posts to bring in advertising.
“Using
AI models known for making up facts to produce what only look like news
websites is fraud masquerading as
journalism,” said Crovitz, a former publisher of the Wall Street Journal.
OpenAI didn't
immediately respond to a request for comment, but has previously stated that it uses a
mix of human reviewers and automated systems to identify and enforce against
the misuse of its model, including issuing warnings or, in severe cases,
banning users.
Giansiracusa,
the Bentley professor, said it was worrying how cheap the scheme has become, with no
human cost to the perpetrators of the fraud.
Before,
it was a low-paid scheme. But at least it wasn’t free,” he said. “It’s
free to buy a lottery ticket for that game now.”
The
Godfather of A.I.’ Leaves Google and Warns of Danger Ahead …… NYT
/ 01 May 2023
Extract :
Geoffrey Hinton was an artificial intelligence
pioneer. In 2012, Dr. Hinton and two of his graduate students at the University
of Toronto created technology that
became the intellectual foundation for the A.I.
systems that the tech industry’s biggest companies believe is a key to
their future.
On
Monday, however, he officially joined a growing chorus of critics who say those
companies are racing toward danger with their
aggressive campaign to create products based on generative artificial
intelligence, the technology that powers popular chatbots like ChatGPT.
“I console myself with the normal excuse: If I
hadn’t done it, somebody else would have,” Dr. Hinton said
But
gnawing at many industry insiders is a fear that they are releasing something dangerous into the wild.
Generative A.I. can already be a tool for
misinformation. Soon, it could be a risk to
jobs. Somewhere down the line, tech’s biggest worriers say, it could be
a risk to humanity.
“It is hard to see how you can prevent the bad
actors from using it for bad things,” Dr. Hinton said.
Several days later, 19
current and former leaders of the Association for the Advancement of Artificial
Intelligence, a 40-year-old academic society, released their own letter warning
of the risks of A.I.
“Maybe what is going on
in these systems,” he said, “is actually a lot better than what is going on in
the brain.”
As companies improve their A.I. systems, he believes, they become increasingly
dangerous.
Look at how
it was five years ago and how it is now,” he said of A.I. technology. “Take the difference and
propagate it forwards. That’s scary.”
Internet will be flooded with false photos, videos and text, and the average person will “what is true anymore.”
Today, chatbots like ChatGPT tend to
complement human workers, but they could replace paralegals, personal assistants, translators and others who
handle rote tasks.
“It takes away the drudge work,” he said. “It might take away more
than that.”
Down the road, he is worried that future
versions of the technology pose a threat to humanity because they often learn unexpected behavior
from the vast amounts of data they analyze. This becomes an issue,
he said, as individuals and companies
allow A.I. systems not only to generate their own computer code but actually
run that code on their own.
And he fears a day when truly autonomous
weapons — those killer robots — become reality.
“The idea that this stuff could actually get smarter than people
— a few people believed that,” he said. “But most people thought it was way
off. And I thought it was way off. I thought it was 30 to 50 years or even
longer away. Obviously, I no longer think that.”
But Dr. Hinton believes that the race between Google and Microsoft and others will escalate into a global race that will not stop without some sort of global regulation.
But that may be impossible, he said. Unlike with nuclear weapons, he said, there is no way
of knowing whether companies or countries are working on the technology in
secret.
The best hope is for the world’s leading scientists to collaborate on ways of controlling the technology.
“I don’t think they should scale this up more until they have
understood whether they can control it,” he said.
Dr. Hinton said that when people used to
ask him how he could work on technology that was potentially dangerous, he
would paraphrase Robert Oppenheimer, who led the U.S. effort to build the
atomic bomb: “When you see something that is technically sweet, you go ahead
and do it.”
He does not say that anymore.
Social
Networks Want to Be Conversational AI’s Killer App …………… Bloomberg /
01 May 2023
Extract :
Over the last month, a few
hundred million Snapchat users got a new best friend: a chatbot named “ My AI.”
The program, which sometimes dubs itself
“Sage” when you ask what it prefers
to be called, is powered by OpenAI’s
powerful artificial intelligence tool, ChatGPT.
Users asked the chatbot to pretend to be their boyfriend and to do their homework, quizzed it, teased it, and got it to reveal its awareness of
their location.
But Sage also portends something else — the imminent collision of generative AI tools like ChatGPT and social media.
Mark Zuckerberg said that conversational AI is coming soon to
social networks like Facebook, Instagram and WhatsApp.
“I think there’s an opportunity
to introduce AI agents to billions of people in ways
that will be useful and meaningful,” Zuckerberg told investors.
But Zuckerberg and Snap CEO
Evan Spiegel are now suggesting that social, not search, might actually be AI’s killer
app — serving as a sort of ever-present
virtual assistant who can suggest funny videos and give you clever ideas about what to say in group chats.
For Liz Perle, a former
Instagram employee and Gen Z consultant, the more pressing concern is whether
young users will use Sage
and sites like ChatGPT
to take academic shortcuts.
Simply put, chatbots like Sage aim to entice users to devote more time and attention to their social
media apps. And that’s the gold standard for any social network
— for better, and way too often, for worse.
No comments:
Post a Comment