Commit Graph
4 Commits
Author SHA1 Message Date
Jesse Zhang a12017f31e Reorganize artifacts by model and harness 2026-06-13 12:59:01 +01:00
Jesse ZhangandClaude Fable 5 8acf16262f Rename Claude Code combination ids to the -cc suffix; refresh the Opus 4.8 mythos build
claude-fable-5-code -> claude-fable-5-cc, claude-opus-4-8 ->
claude-opus-4-8-cc (the entry id doubles as the outputs/ folder name).
The Opus mythos-craft artifact is a newer build of the same one-shot
provenance.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-06-10 23:07:51 +01:00
Jesse ZhangandClaude Fable 5 42efab56e2 Register the Opus 4.8 mythos-craft run (Claude Code, Max)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-06-10 22:42:31 +01:00
Jesse ZhangandClaude Fable 5 bf23fc4168 One ballot per matchup + rating-aware matchmaking; register Opus 4.8 as pending
Every (voter, case, pair) now gets exactly one vote: the client sampler
only draws matchups the browser hasn't voted on (with a graduation state
once all are spent, counter shows voted/total pairs), and the worker
normalizes pair order on insert under a unique (ip, case, pair) index so
side-swapping can't double-count. Daily IP cap drops 300 -> 200 since a
voter graduates at ~171 pairs today.

Matchmaking is now active rather than uniform: unvoted pairs are drawn
with weight closeness/(1+battles) — close ratings and under-played
matchups surface more, unrated combos get placement matches first — with
a 25% pure-exploration floor. Ratings come from the community pool (60s
cached) and fall back to local votes. Rankings stay Bradley-Terry.

Also registers the empty outputs/claude-opus-4-8/ folder as a pending
registry entry.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-06-10 20:38:10 +01:00