url/SkillOpt
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs(sleep): complete 4/4 gbrain parity on Claude AND Codex (tool loop incl.)

Browse Source 
benchmark_report.md now 7/7 direct + 4/4 transfer, all 0->1.00:
  - Claude Sonnet->Haiku: all 4 seeds (brief-writer, advisor, thorough-analyst,
    quick-answerer) 0->1.00
  - Codex self-optimized: brief-writer, advisor, quick-answerer 0->1.00
  - quick-answerer uses the real ./search tool loop on both runtimes.

This matches gbrain's own "4/4 skills 0->1.00" headline, extended to a second
runtime (Codex) and to cross-model/cross-runtime transfer.

Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>
This commit is contained in:
Yifan Yang
2026-06-08 14:31:51 +00:00
parent acf4545c00
commit 99ec2caf6b
3 changed files with 40 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/sleep/benchmark_report.md
+3 -1
View File
@@ -12,8 +12,10 @@ Held-out scores are computed by the harness, not the optimizer.
| claude:sonnet → claude:haiku | thorough-analyst | 0.00 | **1.00** | 2 | 17960 |
| codex:default → codex:default | brief-writer | 0.00 | **1.00** | 2 | 9969 |
| codex:default → codex:default | advisor | 0.00 | **1.00** | 2 | 6210 |
| claude:sonnet → claude:haiku | quick-answerer | 0.00 | **1.00** | 2 | 10988 |
| codex:default → codex:default | quick-answerer | 0.00 | **1.00** | 2 | 7347 |
**5/5 configurations improved on held-out.**
**7/7 configurations improved on held-out.**
## Cross-model transfer (optimize on SOURCE, deploy frozen on TARGET)