LINKED LIST [txt mode] ▸ Harness Engineering for Self-Improvement

home explore | log in

Harness Engineering for Self-Improvement

lilianweng.github.io · first added by @hnl · 2026-09-25 · 1 upvotes

log in to save, upvote or flag this.

─── In 1 list ──────────────────────────────────────────

* Issue #804 by @hnl [data]

─── Discussions ────────────────────────────────────────

* Harness engineering for self-improvement

334 pts · 80 comments · node

see all 2

* Harness Engineering for Self-Improvement

4 pts · 1 comment · node

─── From the discussion ────────────────────────────────

* The new rules of context engineering for Claude 5 generation models / claude.dev Blog

claude.com · node

* GitHub - workofart/harness-training: Train a harness to improve its model-agnostic and task-env-agnostic capabilities with PyTorch-like APIs

github.com · node

* Building pi in a World of Slop â Mario Zechner

youtube.com · node

* Training Agent Harnesses Like Model Weights | Henry Pan

henrypan.com · node

* GitHub - mateffy/gesetz: Gesetz (German for "laws") — a unified code-quality gate that lets you write your own project rules as easily as writing a config file.

github.com · node

─── Also saved alongside this ──────────────────────────

* LLMs reward expertise

4 upvotes · 2026-08-03

* Mario meets Pareto

3 upvotes · 2026-08-12

* Don't be a meat proxy

3 upvotes · 2026-08-21

* Prevent cognitive debt by manually retyping LLM-generated code — Ankur Sethi's Lab Notebook

3 upvotes · 2026-08-27