Neel Nanda: embedded evaluators are a great first step, but we need enforceable agreements
NeelNanda5 · x · 2026-09-13
- DeepMind researcher Neel Nanda responds to the labs' embedded evaluator commitments, calling them a fantastic first step.
- But he cautions that without an agreement to enforce them, embedded evaluators risk being empty words — "we need to see more here."
Related event: Anthropic CEO Dario Amodei Calls for Slowing Frontier AI Development(203 posts)→
More from Safety
- Frog and Toad meme nails the HSM paradox: keys stay safe, but compromised servers can still sign — rickasaurus · 2026-10-31
- Former US Chief Data Scientist DJ Patil publishes memo on the AI cybersecurity reckoning — matt_slotnick · 2026-10-31
- Why an AI military takeover is unlikely: armies won't hand over the reins — S_OhEigeartaigh · 2026-10-31
- Heads Of Security: paper pinpoints and rewires attention heads behind prompt injections — jonasgeiping · 2026-10-31
- House Democrats resolution: no bailouts for failing AI companies — your data goes to bankruptcy court — alex_verem · 2026-10-31
- Amazon Echo kills local voice storage: everything goes to the cloud from March 28 — alex_verem · 2026-10-31