Yifan Yang 9de9220214 docs(sleep): add cross-model scaling results (nano +11.9) and hyperparam ablation (#89) ...

Update RESULTS.md with:
- §2: GPT-5.4-nano target yields +11.9 pt (0.560→0.679) on SearchQA —
  2× the GPT-5.5 gain, demonstrating bigger benefit where headroom exists
- §4: Hyperparameter sweep confirms shipped defaults are optimal

Co-authored-by: Claude Opus 4 <noreply@anthropic.com>

2026-06-26 01:40:58 +08:00

..

guide

…

reference

…

sleep

docs(sleep): add cross-model scaling results (nano +11.9) and hyperparam ablation (#89)

2026-06-26 01:40:58 +08:00

superpowers/specs

…

contributing.md

…

guideline.html

…

index.md

…