Amid CoT monitoring buzz, one video offers a glimpse into how LLMs actually think

kastnerkyle · x · 2026-09-05

Against the backdrop of recent debates on looping architectures and chain-of-thought monitoring, @garygarywang highlights a video he calls one of the most relevant resources for understanding LLM inner workings—with and without CoT—and how reasoning relates to model depth.

Original post →

More from AGI Musings

AGI Musings channel →