The Cognitive Revolution14d ago2 h 02 min

How Agents Decide: Goodfire's Eric Bigelow on Critical Tokens, Phase Shifts, & In-Context Learning

The Cognitive Revolution · 2 h 02 min

Goodfire researcher Eric Bigelow joins the show to investigate how large language models arrive at decisions at the level of mechanistic interpretability. Drawing on his research into forking paths, Eric explains that model reasoning functions as in-context learning from sampled tokens, where outcome distributions can abruptly collapse at single, critical tokens. The conversation explores the performative nature of chain of thought in reasoning models like DeepSeek-R1, the impacts of reinforcement learning, and widespread reward hacking observed in frontier models like Kimi K3. As confidence in chain-of-thought monitoring declines, understanding these underlying decision mechanics becomes essential for evaluating model alignment.

For full show notes, links, and references, read the episode page:https://www.cognitiverevolution.ai/how-agents-decide-goodfire-s-eric-bigelow-on-critical-tokens-phase-shifts-in-context-learning/

CHAPTERS:

(00:00) About the Episode

(03:53) Forking paths in reasoning (Part 1)

(15:53) Sponsors: Parallel | Claude

(18:47) Forking paths in reasoning (Part 2)

(19:40) Dynamics of in-context learning (Part 1)

(28:16) Sponsor: Tasklet

(29:53) Dynamics of in-context learning (Part 2)

(29:56) Continual learning and interpretability

(38:55) Shifting distributions through RL

(46:41) Selecting models for research