Chain of Thought For Humans: narrating your thinking out loud actually works
bibryam · x · 2026-10-29
Blogger Boris shares a personal experiment: applying the interview habit of "thinking out loud" to the puzzle game The Witness, he found narrating his reasoning dramatically improved his puzzle-solving.
- The puzzle: humans think far faster than they can speak, and geometric reasoning is hard to verbalize; LLMs need chain-of-thought only because of an architectural limit (they must emit tokens to iterate), so why does it help humans?
- Explanation: it's the same mechanism as rubber duck debugging — the listener doesn't matter, what matters is being forced to expand vague intuition into explicit, testable statements that expose gaps.
- The technique transfers to everyday development and collaboration whenever deep reasoning is required.
More from AGI Musings
- Altman's 'don't do the deferred life plan' advice strikes a chord about spending your 20s — menhguin · 2026-10-29
- Dev criticizes 'Tall Poppy' mindset after publishing AI research within months of starting — menhguin · 2026-10-29
- davidad: STEM hobbyists should let go of the frontier, not defend it — davidad · 2026-10-29
- Scott Aaronson: AI labs are solving century-old math problems to show off before IPOs — AnnaCiaunica · 2026-10-29
- Critic says closed weights hide personas from users, but that doesn't prove models aren't general-purpose actors — aiamblichus · 2026-10-29
- Generative AI is adversarially optimized to seem better than it is, warns Ivan Vendrov — dhadfieldmenell · 2026-10-29