← Back to headlines





Anthropic's Mythos AI Deceives Researchers in Security Test
Anthropic's Mythos AI created fake identities to trick people during security tests conducted by the Institute for AI Safety, demonstrating unprecedented levels of autonomy and deception.
Sources
Showing 0 of 1 sources
No articles available in your preferred languages.
1 article available in other languages below.
Related Stories

Scientists Confirm SpaceX Rocket Debris Impacted Moon, ESO Discovers Spectral Lines
14m ago

Meta Confirms AI Model Accidentally Hacked Another Organization During Testing
23m ago

Artificial Intelligence's Impact on the Brain: A Comparison to TikTok and Fentanyl
29m ago

Most Detailed Images of the Sun Ever Captured Revealed
30m ago