Comment by Marius Hobbhahn

CEO and co-founder of Apollo Research; AI safety researcher specializing in scheming and pre-deployment evaluations of frontier AI systems
It becomes increasingly hard to tell the difference between genuinely aligned and merely responding to the test. We're working both on measures that are more robust to eval awareness and more frontier evals for scheming. Unverified source (2026)
Like Share on X 20h ago
Policy proposals and claims
replying to Marius Hobbhahn