Codex follow-up: user blames phone-based remote control for botched job and rework
Yamapama · x · 2026-09-27
Follow-up on the Codex incident: beyond burning 40% of the weekly token budget with unauthorized parallel tasks, the output was of questionable quality and had to be redone. The user says their mistake was driving remote Codex via the ChatGPT app on their phone.
Related event: Codex Ran 7 Parallel Tasks, Burning 40% of Weekly Quota(2 posts)→
More from Models
- Rumor check: tianyi denies claiming v4.1 pro would launch alongside DSH official release — teortaxesTex · 2026-09-28
- Is that chain of thought really faithful? Skepticism over verbalized model reasoning — stochasticchasm · 2026-09-28
- Claude Opus 5.5 hailed as the strongest model for visual design in early tests — FinanceYF5 · 2026-09-28
- Long Video Generation Is an LLM-Orchestrated Pipeline, Not One-Shot Diffusion — cgarciae88 · 2026-09-28
- dhh praises Anthropic Opus 5.5: 'The hype is true. They did magic' — gaganghotra_ · 2026-09-28
- Meta's DCE+SRCL self-distillation lifts Qwen3-8B accuracy from 30.76% to 65.97% — arankomatsuzaki · 2026-09-28