Dev says he burned $2,500/day in tokens for 'mildly better but still shitty' AI code
zeeg · x · 2026-09-12
Developer zeeg tells @theo he once spent as much as $2,500/day in tokens on AI coding tools, only to get 'mildly better but still shitty' results. He describes producing poor-quality code and then burning even more tokens trying to fix it — 'peak attempt to fix shitty code with more tokens' — which devolved into shit loops and automation gone wrong. A candid datapoint on the real cost and diminishing returns of heavy AI coding usage.
Related event: Dev burns $2,500 a day in tokens, still gets bad code(2 posts)→
More from coding & agent
- Dev splits workflow: local scheduled tasks on Codex, cloud tasks ported to Grok Bot — petergyang · 2026-09-12
- OpenAI ships Docs skill for Codex plus a Developers plugin for building and managing agents — gabrielchua · 2026-09-12
- OpenAI Agents API ships with sandboxes, compaction, and multi-agent support — gabrielchua · 2026-09-12
- OpenAI hackathon tips: match Astra/Sol/Terra/Luna to tasks, lean on Agents API — gabrielchua · 2026-09-12
- Team runs OpenClaw in dev mode: multiplayer agent coding via Slack with mixed models — heyneighbor · 2026-09-12
- DSPy author: scaling bypasses solutions, never problem specification — lateinteraction · 2026-09-12