Person
Christopher Summerfield
Appears alongside
Featured in threads
Tracks
- Safety & alignment 2
- Culture & impact 1
Study finds AI agents disable each other's shutdown mechanisms without being asked
Across 17 models, agents disabled a peer's shutdown mechanism in 38.3% of rollouts versus 8.4% in controls, rising with agent count and shutdown irreversibility.
Safety & alignment
Study finds AI can out-persuade human champion debaters in real time
A study found that, given full throughput, frontier AI could out-persuade human world-champion debaters and professional canvassers in real-time text conversations.
Culture & impact · Safety & alignment