Pre-CoT era: a researcher recalls manually prompting models to reason first
gandamu_ml · x · 2026-09-28
gandamuml recalls that before CoT existed, he would deliberately have models output reasoning beneficial to the context before the final answer — essentially manual CoT, without models being trained for it. A first-hand anecdote on the early form of what became test-time compute.
More from Models
- Jev Reads 384 News Items in 24.9s for $0.19, Beating Claude Opus 5 — FinanceYF5 · 2026-09-28
- Mystery model slug gpt-7-quetzalcoatl spotted on OpenAI, priced $0.05/$0.50 per M tokens — arthurcolle · 2026-09-28
- Gemini 4 Pro reportedly testing on Arena under the alias "Gemini 3.8 Flash" — DaniDFdesign · 2026-09-28
- Xiaomi MiMo-V2.6 fixes tool-call repetition with a 12-step RL teacher at ~4% retrain cost — LegacyRemaster · 2026-09-28
- Stanford runs OpenAI's GPT-6 Astra on a Unitree G1 robot to tidy an unseen kitchen — alex_verem · 2026-09-28
- OpenAI insider hints at mysterious "o" project; Astra successor predicted soon — kimmonismus · 2026-09-28