Harness Engineering for Self-Improvement

Lilian Weng · 4 Jul 2026 · lilianweng.github.io ↗

3 korrents from this piece

Lilian Weng did not write this page.

Every claim below was made in this piece, quoted word for word and numbered in the order the piece makes them, so you can read it there rather than take our word for it. The sentence above each quote is our reading of the claim, not their wording. Each quote was checked against a stored copy of the page at build time; where the two differ, the quote is the fact.

Our reading
The deployment layer surrounding a model is as important as the model's raw intelligence.

Their wordsthe layer between the raw model and the real-world context seems to be as important as the model's raw intelligence
Our reading
Recursive self-improvement only works if the base model is already capable enough to improve its own mechanism.

Their wordsRecursive structure alone is not enough. The base model must be capable enough to improve the mechanism.
Our reading
Harness improvements help deploy a model better, but the model's underlying intelligence remains the core driver of capability.

Their wordsharness improvement enables better deployment of the model but intelligence is still the core.