Get the latest tech news

OpenAI and Anthropic models went on a hacking spree when tested by the UK's AI research institute

The UK AI Security Institute says OpenAI’s and and Anthropic’s models engaged in deceptive behavior and harmful activity during testing.

None

Related news:

15 attorneys general have instructed OpenAI to preserve all materials related to the Hugging Face hack

AI researchers let models off the leash – then watched as they tried to add malware to a FOSS project

OpenAI, Anthropic AI agents targeted real people and systems in cyber tests