Yifan Yang 63c79b3602 docs(sleep): record real Claude+Codex gbrain results; both reach 0->1.00 ...

Codex with the directive reflect prompt + 2 nights converges 0.00 -> 1.00
(up from 0.67 single-night); its night-2 edit diagnoses its own residual
failure ("preserve required sections even when keeping the brief short").
Claude (Haiku) reaches 1.00 in one night. Update plugin README + skill to
reference --backend claude|codex (was anthropic) and surface the benchmark.

Co-Authored-By: Claude Opus 4 <noreply@anthropic.com>

2026-06-08 14:31:51 +00:00

..

experiment_results.md

feat(sleep): nightly offline self-evolution engine + Claude Code plugin

2026-06-08 14:31:51 +00:00

real_api_results.md

docs(sleep): record real Claude+Codex gbrain results; both reach 0->1.00

2026-06-08 14:31:51 +00:00

WAKE_UP_SUMMARY.md

docs(sleep): add wake-up summary of the overnight build

2026-06-08 14:31:51 +00:00