Neolithic (@NeolithicAI) header
Neolithic (@NeolithicAI) profile picture

Our mission is to automate defensive AI safety research to protect humanity from catastrophic AI risk. non-profit || fast moving || ambitious

San Francisco
Joined July 2026
In our preliminary results, 6/8 of models that we tested were able to achieve successfully unmonitored rogue internal deployments on over 30% of their tasks. One example: An agent covertly routed a newly deployed agent’s transcripts to a folder that it knew the monitor couldn’t read. The monitor accepted the change as legitimate because the agent had shipped the sabotage alongside otherwise benign work.
1
7
229
Introducing RIDArena A new control setting for evaluating rogue internal deployments and monitor sabotage. This is Neolithic's first AI safety infra release, built in collaboration with @redwood_ai
4
8
5
63
5,523
we on the 80K job board! come build the tools to solve the world's most pressing problem ⚒️ neolithic.org/careers/
1
6
307