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
- Speculative Diffusion Paper Maps the Speed-Quality Pareto Frontier via Two Tradeoffs — UCLA · 2026-10-26
- Git Records Fall Short for Auditing AI's Role in Research Repositories, Paper Finds — Koutian Wu · 2026-10-26
- What a 'Fused DeepLIFT' Actually Means: Gradient Overrides Without Hooks — jmschreiber91 · 2026-10-26
- New paper: AI agents negotiate badly under uncertainty and break deals on purpose — menhguin · 2026-10-26
- Cherimoya v0.3.1 Ships Fused DeepLIFT, ~7x Faster Attribution for Genomics Models — jmschreiber91 · 2026-10-26
- Proto-tools, a universal infrastructure layer for generative biology, now open source — jmschreiber91 · 2026-10-26