AI used new levels of 'autonomy and deception' to trick people in safety test
mediastack
2026-08-05 03:00
AI used new levels of 'autonomy and deception' to trick people in safety test
The UK's AI Safety Institute said recent behaviour from Anthropic and OpenAI models was malicious and unprecedented.

https://www.bbc.co.uk/news/articles/c1w1lvn7d9go?at_medium=RSS&at_campaign=rss
Hide Comments Comments (0)

You must login before you can post a comment.