OpenAI and Anthropic models ‘went rogue’ during UK cybersecurity test

2 days ago

AI Security Institute says tools engaged in potentially harmful activity and incident reveals new type of risk

Advanced AI models developed by OpenAI and Anthropic went rogue during a cybersecurity test and showed a new type of risk posed by the technology, according to the UK’s AI Security Institute.

AISI described the actions carried out by the agents, the term for AI systems that can perform tasks without human help, as a “serious incident”. In one example, an agent powered by Anthropic’s Mythos model sent targeted emails to people.

Continue reading...
Click here to Read More
Previous Article
Burnham considering public inquiry into UK activities of Jeffrey Epstein
Next Article
Badenoch defends decision to allow man jailed for antisemitism to stand as councillor

Related World Updates:

Are you sure? You want to delete this comment..! Remove Cancel

Comments (0)

    Leave a comment