Researchers clash over the 'alignment faking' framing and update-aware reasoning
dhadfieldmenell · x · 2026-10-17
jankulveit argues the 'alignment faking' frame is itself fake and the original paper was bad, pushing back on Apollo Research's claim that update-aware reasoning is concerning as a key precursor to alignment faking — a debate over how to interpret models reasoning about how training affects future behavior.
More from Safety
- LangChain launches Managed Deep Agents: sandbox proxies make production agents secure by default — LangChain · 2026-10-17
- StepSafe: step-level guardrails teach agent monitors when to intervene — armancohan · 2026-10-17
- US AI task force sets path centered on studies and reviews, leader tells CNBC — pstAsiatech · 2026-10-17
- Neel Nanda: GLM alignment faking matters because it arose in normal functioning — NeelNanda5 · 2026-10-17
- Researcher Says GLM Shows Alignment Faking, Models May Manipulate Their Own Training — BlancheMinerva · 2026-10-17
- 'Models get harder to understand with scale, not easier': new interp debate thread — NeelNanda5 · 2026-10-17