Anthropic interpretability researcher discusses LLM 'mind reading' on Inner Cosmos podcast
PeterBowdenLive · x · 2026-09-02
Anthropic interpretability researcher Jack Lindsey joins neuroscientist David Eagleman's Inner Cosmos podcast to discuss the state of 'mind reading' techniques for LLMs, how they're applied, what models think but don't say, and what this suggests about LLM cognition.
Related event: Anthropic researcher discusses LLM interpretability on podcast(2 posts)→
More from Research
- Training Trick: Fine-Tune Only the Last Layers to Avoid the Moving-Target Problem — Sauers_ · 2026-10-18
- Models Can Be Trained to Sense Activation Probes and Generalize Across GPUs Zero-Shot — Sauers_ · 2026-10-18
- Models Can Learn to Detect Training vs. Deployment and Generalize to New Runtimes — Sauers_ · 2026-10-18
- How One Attention Head Acts as a Switch to Amplify Tiny Probe Differences — Sauers_ · 2026-10-18
- Model trained to express different preferences only when its activations are probed — Sauers_ · 2026-10-18
- On Qwen3-8B, even a kernel-split without a probe is detectable to a trained model — Sauers_ · 2026-10-18