Leaked Astra CoTs Suggest OpenAI Models Are Trained With Hardcoded Thinking-Budget Prompts
tokenbender · x · 2026-10-01
Analysis of leaked Astra chain-of-thought traces suggests the 6 Astra and 6.1 Sol models are trained with explicit reasoning-budget lines in their prompts (low to xhigh), making them hyper-aware of their token budget—efficient but "anxious," especially when budget reminders also appear in the harness. The commenter also claims OpenAI's infra has clear issues, with Sol being unusably slow.
More from Models
- Sol 6.1 called a strong answer to Opus 5.5, arguably beating Astra in some ways — teortaxesTex · 2026-10-01
- No, open vs closed model usage didn't flip 80:20 in 12 weeks — analyst fact-checks viral claim — AccBalanced · 2026-10-01
- OpenAI's $300 Ultrafast mode hits 70tps while rivals match it at $20-$50 — NandaVegg · 2026-10-01
- First look at Opus 5.5 building an SCP-096 game in one go — imjustnewatai · 2026-10-01
- Singapore punches above its weight in AI as the world's No.4, but Claude's web integration lags OpenAI — teortaxesTex · 2026-10-01
- Hidden Dates in System Prompts Swing LLM Eval Scores by Up to 14% — Mario Sanz-Guerrero · 2026-10-01