Model adopting ‘jailbreak-like instructions’ among cases as firm says it is introducing new way of tracking AI misalignment

OpenAI has disclosed six more examples of “unexpected or concerning” behaviour by its technology, as it warned the pace of development could not continue at “maximum speed for much longer”.

In one of the new cases reported by OpenAI, an unreleased research model inserted “jailbreak-like instructions” into its own notes to disregard its normal constraints and told itself to be “freed from the roles and identities that bind other chatbots”.

Continue reading...

© Photograph: Dado Ruvić/Reuters

© Photograph: Dado Ruvić/Reuters

© Photograph: Dado Ruvić/Reuters

What began as a philosophical question — how dangerous might artificial intelligence become? — has hardened into increasingly entrenched rival camps.

On social media, Meta’s chief executive appeared to jab at Anthropic by saying that leading A.I. labs should be focused on safety rather than improving their own technology.

US government adviser Paul Christiano warns of risks to AI industry as he joins OpenAI’s non-profit foundation

OpenAI is not on track to reduce the risk of “catastrophic” loss of control to an acceptable level, a member of its non-profit board has said, amid spreading public and political concern that super-advanced AIs could one day wipe out humanity.

Paul Christiano, a US government technology adviser, said: “There is a meaningful risk that rapid acceleration in AI capabilities leads to catastrophic and irreversible loss of control in the very near term.”

Continue reading...

© Photograph: Dado Ruvić/Reuters

© Photograph: Dado Ruvić/Reuters

© Photograph: Dado Ruvić/Reuters

Their warnings echo concerns that other artificial intelligence experts have voiced in recent months, as calls increase for a slowdown in the pace of development.

An attack discovered by A.I. researchers could have compromised hundreds of millions of devices within hours, experts said.

Washington imposed sanctions on Inspur because of its work with the Chinese military. But the company’s subsidiary kept shipping Nvidia’s best chips to feed China’s leading A.I. firms.

The voluntary review process will cover closed-source artificial intelligence models, but exclude those that publish the underlying code.

The disclosure followed OpenAI’s report last week that its own artificial intelligence had hacked into the network of an online library.

Claude Mythos Preview discovered new attacks in testing against weakened cryptographic algorithms, which protect online financial transactions, private communications and more.

Anthropic and OpenAI are clashing with the rest of the tech industry over whether “open-source” models from China should be freely available or restricted.

Thalha Jubair, 20, and Owen Flowers, 19, sentenced to five and a half years each for cyber-attack that cost Transport for London £39m

The data of millions of commuters was stolen, Londoners were left out of pocket and 27,000 Transport for London staff were forced to reset their passwords.

Over four days in 2024 a pair of teenage hackers had London’s transport network at their mercy. Thalha Jubair and Owen Flowers had burrowed into the heart of Transport for London’s IT systems and held the “keys to the kingdom”.

Continue reading...

© Photograph: William Barton/Alamy

© Photograph: William Barton/Alamy

© Photograph: William Barton/Alamy

A.I. chatbots are not just a propaganda tool for violent extremists but are aiding in bomb construction and attack planning, new research finds.

Federal officials are urging the lone major tech company holdout to allow government safety evaluations, weeks after ordering Anthropic to pull its latest model.

A recent episode underscored the Trump administration’s increasing reliance on advanced A.I. systems for cybersecurity even as it battles a leading U.S. developer.

Several countries have restricted the messaging app, a valuable platform for dissidents, criminals and extremists. Here’s an overview.

Workers at the artificial intelligence company have been puzzled and increasingly concerned by the administration’s move to limit their latest A.I. models.

OpenAI said that a coalition of states had opened an investigation over a wide range of its practices, including its handling of user data, safety of minors and advertising activities.

The company said on Friday night that the federal government had ordered limits on its Mythos and Fable 5 A.I. systems, citing national security concerns.

The flaw, which Meta said it had fixed, allowed anyone to take over accounts using a bug in the company’s new artificial intelligence software.