spb/wp29_uqo

Public

Fri, Oct 30, 2026 1
1. Main benchmark complete (288 runs), RC0094 rerun, rubric sensitivity (A-005), R2 stale-input, results draft, induced gate-rejection capture
  …
  Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
  Simon-Pierre Boucher 4 days ago · 1 file +2
Thu, Oct 29, 2026 1
1. Phases 02-05: protocol, harness, viewer/capture, live smoke experiment (4 arms)
  …
  Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
  Simon-Pierre Boucher 4 days ago · 6 files +38

Fri, Oct 30, 2026 1