Neel Nanda: Gemini 4 Argon has Google's most thorough safety report yet
NeelNanda5 · x · 2026-10-14
DeepMind alignment researcher Neel Nanda praises the Gemini 4 Argon safety report as Google's most thorough by far, joking that the model is "so back on the one metric that really matters: length of our safety report." He highlights the loss-of-control, alignment, and monitorability assessments as particularly worthwhile reading.
More from Models
- Snap launches as first fully sub-quadratic LLM in production with constant compute per token — ryanallred · 2026-10-14
- xAI says legacy SuperGrok Heavy plans can't be restored after billing merge mistake — RexDouglass · 2026-10-14
- HyperThink uses a hypernetwork to replace long chain-of-thought with one parameter update — Donggyun Kim · 2026-10-14
- Uberti: background voice cancellation is underparameterized for noisy audio — juberti · 2026-10-14
- Gemini 4 Argon leaps in 3D reconstruction: 81.2 on BuildingBench at ~1/5 cost — Lianhuiq · 2026-10-14
- WebRTC author Justin Uberti: diarization is the wrong path, train LLMs on noise — juberti · 2026-10-14