The special reasoning-trace delimiter tokens used by reasoning models are cosmetic and not required for good reasoning performance.

Added to korrents 18 Jul 2026 · How quotes work · Something wrong? Tell us

Related korrents

Our reading — they may agree, disagree or merely touch the same thing. Closest first: a shared subject counts for most, then how near the wording is.

• Tokens are not the true unit of AI inference, because better models yield more problem-solving per token. PGPaul Graham15 Sept 2026similar wordingCo-founder of Y Combinator and Viaweb
• As labs sell finished white-collar work rather than reasoning traces, Chinese models will lose the ability to distil their way to parity. DPDylan Patel13 Mar 2026similar wordingFounder and chief executive of SemiAnalysis
• Large language models do not reason formally: their performance collapses as a problem is made bigger, in the way a calculator's never does. GMGary Marcus11 Oct 2024similar wordingCognitive scientist, professor emeritus of psychology and…
• Without good intuition for models, treat 100k tokens on smaller models and 200k on the frontier ones as the line past which the quality of your results is probably already degrading. DHDex Horthy15 Jul 2026similar wordingFounder of the agent company HumanLayer
• The aha moment for reasoning models will come from computer use and robotics rather than from scientific discovery, because those are the infinitely verifiable playgrounds. DPDylan Patel3 Feb 2025similar wording

On the map

Open the map on its own page →