747 AI-agent ideas reveal a scaling law for idea descent: +17% per doubling
DimitrisPapail · x · 2026-11-01
Dimitris Papail shares an experiment chart showing 'scaling laws for idea descent': across 747 ideas from four AI-agent campaigns in five days (Codex, Claude Code, two Copilot swarms), best result rose from 0.93× to 2.25× baseline, gaining 17% per doubling of ideas, with an estimated hard ceiling ≈2.39–2.45× around 2,200 ideas. Chart shows Claude Code handing off at 1.95×.
More from coding & agent
- Karpathy's nanochat hits 59K stars: a full LLM training lab in one repo — techNmak · 2026-11-01
- Personal agents' third act: giving your dot ongoing responsibilities — craigsdennis · 2026-11-01
- Hands-on tutorial trains a decision model on Qwen3-0.6B from scratch — dl_weekly · 2026-11-01
- ui-ux-pro-max and 6 more repos giving AI coding tools real design taste — GCWebDesigner · 2026-11-01
- Hex ships stable release: local voice dictation for talking to AI agents on Mac, Windows, Linux — madeofAjala · 2026-11-01
- Personal AI agent race heats up — this prompt migrates your entire setup between agents — EXM7777 · 2026-11-01