OpenAI researcher slams capacity errors that kill overnight agent sessions with no fallback info
willdepue · x · 2026-10-24
willdepue publicly complains he literally cannot use the product: the selected model is persistently at capacity, overnight sessions get interrupted without restarting, and the product won't tell him which models actually have availability or what to switch to. Screenshots show an agent task repeatedly derailed by capacity errors mid-run.
More from Models
- Block Unveils Dessa, a Full-Duplex Speech-Only Model Trained From Scratch With No Text — stochasticchasm · 2026-10-24
- Kimi K3.1 Pro Debuts at #4 on AA Index, Set to Narrow Open-Weights Gap to 3 Points — dbreunig · 2026-10-24
- Dev notes model fixed overthinking with fewer reasoning tokens, suspects benchmaxxing — cedric_chee · 2026-10-24
- Public benchmarks show Kimi K3 beating all OpenAI models, including Astra — bindureddy · 2026-10-24
- First Kimi K3.1 Pro benchmarks compare it against Opus 5.5, Sonnet 5.5 and Gemini 4 — arena · 2026-10-24
- Recursive's 40B Flint Hits ~200 tok/s on M3/M5 Ultra via MLX-VLM with Fused Metal Kernels — timshi_ai · 2026-10-24