OpenAI staffer wants scheduled agent tasks to pin cheaper models to cut overnight API costs
willdepue · x · 2026-10-03
In a follow-up to OpenAI's @romainhuet, willdepue argues scheduled tasks should let users pre-specify the model. He worries that an agent running on Astra might wake up every hour all night and waste significant money compared to Sol — a practical concern about per-run cost control for always-on scheduled agents.
Related event: OpenAI Employee Pitches Agent Inbox, Memory Toggles and Model Presets(2 posts)→
More from coding & agent
- New TLAPS-Bench blog: formally proving correctness of real-world system specs with TLA+ — tianyin_xu · 2026-11-19
- Rivet's lesson: JEV doesn't reason—split severity classification into tiny yes/no prompts — yawnxyz · 2026-11-19
- 16x Microsoft MVP demos a native PowerShell agent built on Microsoft's Intelligent Terminal — dfinke · 2026-11-19
- Musk: Treat Grok Bot like a really smart employee, says most users underuse it — elonmusk · 2026-11-19
- Eve agent tool cuts build time 8x to 6.9s by reusing compiler module graph — evilrabbit_ · 2026-11-19
- Dev shares NL-driven testing UI: 'the best interface is chat' — KlausCodes · 2026-11-19