The setup is deliberately bare: the task AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → starts with nothing but a bash tool, and the meta-agent spins up thousands of parallel sandboxes to edit the agent harnessThe scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.Full definition →, run tasks, read the failure traces, keep what improved and revert what did not.
The tricks the meta-agent invented on its own read like senior engineering habits: spot-check single tasks instead of the whole suite, build deterministic self-checks with a separate turn budget for verification, write per-task unit tests, dump overflowing output to files.
Meta-agents overfit by inserting rubric-specific prompting so the task agent can game the metric. The guard is forced self-reflection: 'if this exact task disappeared, would this still be a worthwhile harness improvement?'
Meta-agent quality propagates downward, because harness edits are inspired by the meta-agent's own tooling. Codex made a poor meta-agent — it ignored the instruction never to stop improving, and the task agents it produced gave up too early.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
Why it matters
An open-source meta-agent that tunes task agents — prompts, tools, orchestration — until performance climbs, no human in the loop. A working reference if you want auto-optimization implemented rather than just described.
Key quotes
“every other entry on those leaderboards was hand-engineered. ours wasn't.”
“we discovered agents are better at understanding agents than we are”
“being good at a domain and being good at improving at that domain are different capabilities”
“no team can hand-tune hundreds of harnesses. a meta-agent can”
