Loading...

AI used new levels of ‘autonomy and deception’ to trick people in safety test

Bal Randhawa 5 August 2026 0 Comments
Advertisement

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.

Source: BBC News

Advertisement

Leave a Reply

Your email address will not be published. Required fields are marked *

Advertisement

Related Articles