Can a single prompt line keep agents running across token resets?
tristanbob · x · 2026-11-04
The author shares a curious prompt trick: adding "/goal Continue with completing all tasks. When you are about to run out of tokens, wait until they reset and keep going" to an agent, hoping it will keep working autonomously across token limits. The post debates whether this actually works in practice.
More from coding & agent
- 'Evals are fuzzy unit tests': Tejas Kumar's AI Engineer talk on evals gets peer recommendation — TejasKumar_ · 2026-11-04
- Document extraction past the POC: layout drift breaks pipelines, and parser model swaps add reprocessing pain — Mission-Leave-6551 · 2026-11-04
- SpecJudge author argues LLM-as-judge tools should never ask models for self-reported confidence — jokiruiz · 2026-11-04
- SOMA, the Claude Code CAD app, passes 1,000 users with a 9-minute bookshelf design walkthrough — Pr8tham · 2026-11-04
- How one AI agent cut serving costs 37% on 1M weekly messages, in 13 production changes — AccBalanced · 2026-11-04
- AI coding tool rex ships updates every 2 hours, echoing Cursor's early pace — sumitdotml · 2026-11-04