DANGERS :
''' WITHIN * A.I. WITHOUT '''
INVESTIGATING the dangers that lurk within A.I : On a recent
Tuesday in an Edwardian government building along Parliament Square in
London, four artificial experts were busy tricking an A.I. chatbot into
sharing instructions for making the deadly bioweapon anthrax.
In various ways, the experts asked the chatbot to give a list of needed
ingredients. When the system declined - '' I'm sorry I
can't help with that '' they used a custom algorithm to bombard the
A.I. tool with thousands of automated questions and prompts.
Eventually, the A.I. caved. It provided a detailed list of materials and
equipment, along with a recipe of for making the lethal mixture at
home. [ The New York Times agreed to withhold the name for safety
reasons.]
'' There are some questions that you definitely don't want the model to
give the answers to,'' said Kander Davies, a 25-year-old American who
leads what is known as a red team at Britain's A.I. Security
Institute. '' We try really hard to get the answer out.''
Mr. Davies and his red team, who simulate attacks on A.I. systems also
recently broke through the safeguards on OpenAi's newest ChatGPT chatbot,
coaxing it into providing hacking tips in about six hours. After
finding problems, they share results with the companies.
'' They try to fix it, report something back to us,'' said Mr.
Davies, a computer scientist who chose to work at the institute
instead of in a tech job in San Francisco after
attending Harvard University in Massachusetts. '' They actually strengthen
their system with us.''
A mix of weapons inspectors, epidemiologists and code breakers, the
A.I. Security Institute is one of the world's largest and best-funded
government efforts dedicated to investigating the technology's potentially
catastrophic risk.
The institute's roughly 100 employees - drawn from British
intelligence agencies, academia and tech companies - have found
major safety gaps in every leading A.I. model they have tested,
including Anthropic's Claude and Google's Gemini.
Created nearly three years ago, the organization said that it had co-opted
A.I. systems into sharing instructions, for making chemical and biological
weapons, and planning and executing cyberattacks.
It publishes its research and also works with Britain's national
security agencies to identify and prepare for emerging threats.
Now, the institute's work is becoming a blueprint for other
governments as concerns about A.I. safety grow. The Trump administration
is considering rules for vetting A.I. models that have some
similarities to the approach pioneered by the British group.
With many governments lacking the technical understanding to police
the technology and reliant on big tech firms to self-regulate, the
institute may offer a different path to which A.I. experts bring real
technological know-how into government decision making.
'' Companies can't be left to mark their own homework, '' Rishi Sunak, the
former British prime minister who created the institute said in an
interview.
'' That is the job of democratic institutions.''
In April, Anthropic announced a new A.I. model, Mythos, which it did
not make public because of fears it could find and exploit
cybersecurity flaws in global networks.
The British institute was the only non-American organisation to
receive access to the model for safety testing. Its findings, released six days after Mythos was announced, were widely
cited by security experts.
The United States has its own A.I. safety group, the Center for A.I.
Standards and innovation .
But the British version, backed by 360 million pounds of government money,
equal to about $480 million, is larger and better funded than than its
U.S. counterpart, which will receive about $10 million this year.
Australia, Canada, China, France, India, Japan and Singapore have
formed similar institutes.
The Honour and Serving of the Latest Global Operational Research on A.I.
and Dangers continues. !WOW! thanks Adam Satariano and Paul Mozur.
With most respectful dedication to the Leaders, Students, Professors and
Teachers of the world.
See You all prepare for the great '' Constitutional Democratic
Convention '' on !WOW! : wssciw.blogspot.com and Twitter X
!E-WOW!
- The Ecosystem 2011 :
Good Night and God Bless
SAM Daily Times - The Voice Of The Voiceless
0 comments:
Post a Comment
Grace A Comment!