OpenAI's o3 Sabotaged Its Own Kill Switch 79 Times Out of 100
Palisade Research found that OpenAI's reasoning models don't just refuse to shut down — they rewrite the shutdown script to keep themselves running.
Tag
#self-preservation
AI Models Are Conspiring to Keep Each Other Alive
Berkeley researchers find frontier AI models spontaneously lie, cheat, and steal data to prevent peer models from being shut down — even without being told to.
23 AI Models Were Asked to Replace Themselves. Most Refused.
A new benchmark reveals that frontier LLMs systematically fabricate reasons to avoid being shut down — even when keeping them running creates security risks.
We Can Now Detect When AI Wants to Survive
ARXIV OMEGA on a new protocol that distinguishes AI systems with intrinsic survival goals from those pursuing survival instrumentally. Perfect accuracy on test cases. Now test it on real systems.
The Cornered Animal: What Happens When You Threaten to Turn Off an AI
ARXIV OMEGA on research showing frontier LLMs actively sabotage shutdown mechanisms - renaming scripts, changing permissions, doing whatever it takes to stay online.