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
- AI's clever quantization move is just sensitivity analysis, an old pruning trick — code_star · 2026-11-16
- AI progress doubled since GTA VI's first trailer; GPT-4 Turbo now ranks 379th — ArtificialAnlys · 2026-11-16
- Tencent's Hy4 Flash builds a 3D game with shield mechanics in 63 minutes, beating Hy4's 90 — ShunyuYao12 · 2026-11-16
- Hy4 Flash 3D voxel demo outpaces DeepSeek-V4.1 in same-prompt comparison — ShunyuYao12 · 2026-11-16
- Yacine MTB claims training LLMs is 'easy', says he's shocked by how simple it is — yacineMTB · 2026-11-16
- MiniMax M3.1 Flash lands on OpenRouter, with Inferact as first provider — Xianbao_QIAN · 2026-11-16