Correct LAB protocol: model held constant, codex is pilot-only

↗ view on GitHub · Eli Ziff · 2026-07-28 · 175d5b08

The experiment measures LAB harness vs Beaver harness with the model
held constant per pairing (sonnet-4-6 via headless Claude Code; desktop
qwen via ollama). Codex rows are pilot history - no codex in any
experiment cell. Claude-Code-as-product runs relabeled cc-harness-* as
a side observation. AGENTS.md gains the .CMD-shim argv trap and the
corrected design note.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_018bhP89cYSdEEjHNPnxacns
Repository eliziff/Beaver
Author Eli Ziff <eliasziff@gmail.com>
Authored
Parents 20cdc164
Stats 2 files changed , +45 , -26
Part of Codex integration and hardening

Capture this commit into my fork

Download a Markdown prompt that tells Claude how to port this exact commit into your working tree. Run it via claude -p < capture-commit-175d5b08.md from inside the repo you want the change in.

⬇ Download capture-commit-175d5b08.md