How to stop AI agents going rogue
Source: BBC
Sean McManusTechnology ReporterGetty ImagesAnthropic tested a range of leading AI models for potential risky behaviourDisturbing results emerged earlier this year, when AI developer Anthropic tested leading AI models to see if they engaged in risky behaviour when using sensitive information.Anthropic's own AI, Claude, was among those tested. When given access to an email account it discovered that a company…
This is aggregated or syndicated coverage. Reporting and media belong to the original publisher.
Read the original source at BBC