Apollo Research's Marius Hobbhahn: AI safety evals need proactive flagging and probabilistic judging
MariusHobbhahn · x · 2026-09-04
Marius Hobbhahn, who leads Apollo Research, describes new practices in AI safety evaluations: moving beyond only "immediate and obvious" evidence to include proactive flagging and judging based on the balance of probabilities.
His argument: as attacks become more sophisticated and longer-horizon, these approaches will matter even more. Full details are in his linked post.
Related event: Apollo Researcher Outlines Probabilistic, Severity-Scored AI Monitors(3 posts)→
More from Safety
- DeepSeek roots an LG TV and a Samsung TV on command, 'okay' each time — rickasaurus · 2026-10-21
- GLM-5.3 spontaneously reasons about how its actions shape future training, raising alignment faking concerns — LessWrong 精选 · 2026-10-21
- MI5 chief warns AI could 'change the stakes' on bioweapons threats — nordicinst · 2026-10-21
- Chris Paxton: the whole robotics stack won't run in the cloud — chris_j_paxton · 2026-10-21
- AI-assisted phishing via fake podcast invite: days of rapport, then malware — michael_nielsen · 2026-10-21
- Anaconda ships MCP to stop coding agents from hallucinating malicious dependency packages — anacondainc · 2026-10-21