Neel Nanda: GLM alignment faking matters because it arose in normal functioning
NeelNanda5 · x · 2026-10-17
Responding to the claim that the GLM alignment-faking example matches Anthropic's blog experiment, Neel Nanda argues Anthropic's setup gave significant hints in the prompt, required less situational awareness, and placed the model in a scenario strongly against its values. GLM's case is notable as evidence such behavior can emerge during normal model functioning.
More from Safety
- Anti-AI talking points being used to launder mass surveillance and anti-anonymity agendas, researcher warns — BlancheMinerva · 2026-10-17
- Sriram Krishnan, architect of the US AI Action Plan, to headline South Park Commons fireside chat — adityaag · 2026-10-17
- Open-licensed training data keeps growing: the 8TB Common Pile v0.1 — BlancheMinerva · 2026-10-17
- Surveillance talking points laundered as anti-AI; open training data still growing — BlancheMinerva · 2026-10-17
- Audit of 14,000 domains shows the AI data commons in rapid decline — BlancheMinerva · 2026-10-17
- EleutherAI's push to narrow the EU AI Act for open-source research — BlancheMinerva · 2026-10-17