5 minutes of talking, 12 hours of Claude: one-prompt Opus 5.5 build stuns observers
zetalyrae · x · 2026-09-24
A viral demo shows what one-prompt agentic coding now looks like: the author spoke to his computer for 5 minutes, Opus 5.5 (Claude) worked autonomously for 12 hours overnight, and he woke up to a finished project — full prompt shared. The resharing comment captures the mood: it makes everything else feel insufficiently ambitious, as 'the machines are eating the world.'
More from coding & agent
- OpenRSI launches benchmark testing recursive self-improvement on 1k-GPU clusters with 60+ hour agent runs — ChengleiSi · 2026-09-24
- OpenRSI calls for contributors: turn your research into benchmark tasks for frontier agents — ChengleiSi · 2026-09-24
- OpenAI's Neon Connector Reaches Voice Mode but Project-Level Actions Fail on Missing project_id — koltregaskes · 2026-09-24
- Bug Hunt Bench leaderboard live: 105 planted bugs, score vs cost across frontier models — PawelHuryn · 2026-09-24
- Bug Hunt Bench author says his code-review skill significantly lifts model scores — PawelHuryn · 2026-09-24
- 30 annotations with GEPA prompt optimization boost lead scorer accuracy 43%, cut cost 5x — CShorten30 · 2026-09-24