Codex reasoning-token clustering at 516 may be leading to degraded performance
0x_rs
12 points
1 comment
July 01, 2026
Related Discussions
Found 5 related stories in 149.7ms across 13,038 title embeddings via pgvector HNSW
- GPT-5.5 Codex reasoning-token clustering may be leading to degraded performance maille · 213 pts · July 04, 2026 · 86% similar
- Codex logging bug may write TBs to local SSDs vantareed · 480 pts · June 22, 2026 · 62% similar
- Codex pricing to align with API token usage, instead of per-message ccmcarey · 198 pts · April 05, 2026 · 60% similar
- Codex Plugins epaga · 13 pts · March 27, 2026 · 56% similar
- OpenAI's new $100 tier targets developers hitting Codex limits Brajeshwar · 15 pts · April 10, 2026 · 56% similar
Discussion Highlights (1 comments)
cyanydeez
wonder if theyre basically doing this llamacpp reasoning trick: https://github.com/ggml-org/llama.cpp/blob/master/common/rea... id guess its the harness