Agent-built eval harness spawns subagents via codemode in one durable session
mitsuhiko · x · 2026-11-03
mitsuhiko shares badlogic's trick: a spare agent built an eval harness comparing models on tasks using quickjs/js and Armin's djs/TS. The eval runs via codemode, spawning subagents inside the same pi durable session — a neat agent-orchestration pattern.
More from coding & agent
- Watching three AI agents interview each other in Slack to write docs — aniketmaurya · 2026-11-03
- AI Products Still Feel Single-Player; Team Bots Point to Multiplayer Human-Agent Future — joonasvirtanen · 2026-11-03
- Stanford launches CS329Z on Engineering AI Agents, taught by SWE-agent creator — stanfordnlp · 2026-11-03
- Podcast: opencode's thdxr on open source, harness vs model, B2B vs B2C AI — yenkel · 2026-11-03
- 86.2 Agent Hours With Opus 5.5 Produced a Hyperpop Music Video — apples_jimmy · 2026-11-03
- Matt Shumer shares "Manager Loop": the orchestration trick behind super long-horizon agent builds — mattshumer_ · 2026-11-03