Cluster failures by the fix they would need rather than by symptom. It forces attentionThe mechanism that lets a model weigh which earlier words matter for the word it's currently processing — the core operation of a transformer.Full definition → onto the underlying cause and stops the optimizer overfitting to single cases, because a change that clears a whole cluster tends to generalize.
Verbose traces flood the main context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → fast. Give sub-agents ownership of their own output so the parent only ever sees a summary — that is what makes long-running self-improvement runs survivable.
The leverage is in the meta-layer, not the loop machinery: the instructions, bias rules, playbooks, tools and skills you wrap around the optimization matter more than the optimizer itself.
The bottleneck moved past writing code to everything after it — validating behavior, catching regressions, debugging failures, and keeping evaluations honest as the system evolves and user behavior drifts.
Terms in this piece · Glossary
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.
eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
attention — The mechanism that lets a model weigh which earlier words matter for the word it's currently processing — the core operation of a transformer.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
Why it matters
A methodology for agents that mine their own failures, generate evalA repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.Full definition → from them, and fix issues automatically — closing the loop most teams still run by hand. Read it if "self-improving" currently means you, editing prompts at midnight.
Key quotes
“The bottleneck has moved. It is no longer writing code. It is everything that comes after: validating behavior, catching regressions, debugging failures, and maintaining evaluations and reliability as systems evolve and user behaviors drift.”
“Point it at your agent. Leave it running. Come back to a better agent with evals.”
“Clustering failures is key: Grouping failures by their proposed fix forces you to attack the underlying cause rather than each symptom in isolation.”
“The regression gate is what makes gains compound: Fixed failures become permanent test cases. The system can't backslide past what it's already solved.”
