How agents decide: Goodfire's Eric Bigelow on critical tokens and phase shifts
PeterBowdenLive · x · 2026-10-29
An 88-minute Cognitive Revolution episode with Goodfire researcher Eric Bigelow (Harvard psychology PhD) on how LLMs make decisions: from a mech-interp and cognitive science angle, he explains how critical tokens trigger sudden phase shifts and how models adapt to their own sampled reasoning chains. Host Nathan Labenz notes Eric is the first guest in 400 episodes recommended by an AI.
More from Research
- Weaviate Podcast: MIT PhD's "Machine Studying" lets always-on agents prep without knowing the task — CShorten30 · 2026-10-29
- The singularity's week: 80-year-old cells reset, 25-year-old math disproved by AI labs — rand_longevity · 2026-10-29
- Single-nucleus RNA-seq atlas reveals distinct features of early-onset colorectal cancer in the young — EricTopol · 2026-10-29
- Stanford's ChromBPNet Reads DNA Regulatory Switches Base by Base — RichardsonDx · 2026-10-29
- Determinism in Training Costs Single-Digit Percent, Not 10x — gandamu_ml · 2026-10-29
- Neuron steering struggles at persona creation, failing multi-turn stability — davidad · 2026-10-29