Routing experiment results: delegation only pays off in large harnesses
yb2698 · x · 2026-10-23
Results of the small-model routing experiment: with small harnesses like ipython or Pi, the delegation protocol costs more than running the large model directly. Larger harnesses show a gain, suggesting delegation/orchestration makes sense when a very large model is wired into a big harness. Though the small model handles a notable share of turns, it still accounts for a small fraction of output tokens.
More from coding & agent
- Vercel adds no-account deploys: drag and drop a file to get a live URL — steren · 2026-10-23
- Vercel ships 'vercel deploy --temporary' for ephemeral agent-built deployments — cramforce · 2026-10-23
- Running multiple agents out of one Notion workspace as a shared task board — nbaschez · 2026-10-23
- We tested 12 LLM classifiers — the new classifier hype is LARP — KlausCodes · 2026-10-23
- Dev builds ESP32 desk display showing Claude Code and Codex agent status via local Go helper — tonylook · 2026-10-23
- Let your agent read its own traces: AgentsView + history tool debugging workflow — dbreunig · 2026-10-23