DeepMind Discusses Model Interpretability
GoogleDeepMind · x · 2026-07-11
A Google DeepMind podcast invited @NeelNanda5 to discuss interpretability research, focusing on "reverse engineering" how neural networks learn and think.
Key points include:
- chain of thought can act like scratch paper to help observe model reasoning
- mechanistic interpretability: studying internal mechanisms, not just inputs and outputs
- chain of thought monitoring: using chain of thought as a window for monitoring and security auditing
- Also discussed interpretability techniques, model security auditing, and future developments in this direction
Related event: DeepMind Discusses Chain of Thought and Mechanistic Interpretability(4 posts)→
More from Research
- VidMap uses RoMa coarse matching on all frames, fine-scale only for keyframes — ducha_aiki · 2026-09-11
- Bug Hunt Bench author: leaderboard noise is about 2-3 points — PawelHuryn · 2026-09-11
- PNAS paper shows a tiny billiard-ball system is a universal computer — undecidability lives in two dimensions — eigensteve · 2026-09-11
- New paper: Absolute pose estimation from affine cues and gravity direction — ducha_aiki · 2026-09-11
- LoMa Paper Ships REALLY HardPairs Dataset, Accepted at ECCV 2026 — ducha_aiki · 2026-09-11
- Johns Hopkins Launches Full-Stack Hands-on Robot Learning Class with SO-101 Arm Kits — _krishna_murthy · 2026-09-11