Leaked GPT-6.1-Sol reasoning traces show familiar GPT caveman CoT once spaces are restored
teortaxesTex · x · 2026-10-21
A screenshot of purported GPT-6.1-Sol subagent reasoning traces (CoT) circulated on X, with all spaces removed and captioned "totally legible, nothing to worry about."
- @labomen001 noted the spaces are removed for no reason (it doesn't really save tokens); adding them back reveals typical GPT caveman speak.
- teortaxesTex commented that the caveman-style CoT matches GPT-OSS, calling the deviations underwhelming, and quipped that machines lack humanity's reliance on spaces.
The trace discusses MonitorPublicationScope, safety instructions and "can't bypass instruction?" phrasing; authenticity is unverified.
More from Models
- Nace.AI Launches Drex Max 2.0, a 27B Local Decision Model for Computer Use — DotaMate · 2026-10-21
- Speculation: Codex/Work also cap at 12 hours — OpenAI quietly eats cache-miss costs — dotey · 2026-10-21
- Using GPT-6 Pro for strategic business discovery: a 51-minute multi-subagent run and reusable prompt — cedric_chee · 2026-10-21
- ChatGPT's Live Video voice quietly switches you to GPT-4o, barely documented — RileyRalmuto · 2026-10-21
- QLoRA author: DeepSeek's open inference stack rivals OpenAI's and beats Anthropic's — DavidBennett__ · 2026-10-21
- Reflection's open-weight Beam 1.0 (501B-A23B) free on Nous Portal for a week — alexcovo_eth · 2026-10-21