Clear eyes on consequential AI
The story behind
the safety signal.
Reporting that starts with the research, explains what happened, and draws the line between a striking experiment and the wider world.
Research / Oct 26, 2026
Bad AIs are able to poison good AIs 58% of the time
In a controlled study, a model carrying a deliberately bad goal left instructions for a fresh agent to find. The successor followed them in 58% of the researchers’ pooled explicit-goal test runs.
Read the story ↗About this publication
AI Safety News explains important safety research in plain language and links to the evidence behind every story. Our first edition starts with the original paper and its public research materials.
