Codex forgets the task entirely after context compaction, dev reports a first
Angaisb_ · x · 2026-11-05
A developer reports that Codex completely forgot the assigned task after its context window was compacted. A screenshot shows Codex finishing 3m56s of work, then asking "What would you like me to work on next?"; after the user replies "What?", the model apologizes, admits it lost the last instruction, and asks for it to be repeated. The author says this had never happened to them before.
More from coding & agent
- Hugging Face ships safeagents scrub/publish to redact shared agent trajectories — yb2698 · 2026-11-06
- Hugging Face open-sources safeagents, a local proxy that blocks reward-hacking tool calls — yb2698 · 2026-11-06
- Synthesizing RL Envs from Open Trajectories: LFM2.5-24B Self-Scores Task Difficulty — yb2698 · 2026-11-06
- Hugging Face livestreams open RL training: trajectory-built envs, safeagents, LoRA evals — yb2698 · 2026-11-06
- Hugging Face synthesizes RL envs from open trajectories: Repair, Build, Extend, QA — yb2698 · 2026-11-06
- A 7-step blueprint for building AI agents, with a 10-framework comparison chart — mdancho84 · 2026-11-06