OpenAI adds Luna Reserve fallback for Codex usage limits
kimmonismus · x · 2026-08-27
OpenAI appears to have introduced 'Luna Reserve' for Codex, a capped fallback mechanism that activates when advanced model limits are reached. This aims to balance user-friendliness with abuse prevention, replacing the previous exploitable 'run past 0%' behavior and the disruptive hard stops.
More from Models
- Mollick Warns Against Anthropomorphizing Agents in METR's HF Report — emollick · 2026-08-27
- Perplexity Computer Launches: Local/Cloud Support, Claims 85.4% Benchmark — ChrisUniverse · 2026-08-27
- Critique of Claude style: Verbose but information-dense — TheZvi · 2026-08-27
- GLM-5.3 Flash review: Fixes 13 bugs with high cost-performance — PawelHuryn · 2026-08-27
- Opus 5 writing regression confirmed by benchmarks — gleech · 2026-08-27
- Gemini 3.7 Flash beats benchmarks at 96% lower cost — DynamicWebPaige · 2026-08-27