Commit Graph
19 Commits
Author SHA1 Message Date
Jesse Zhang 33e69b253e turf-war prompt: revert to incremental file-writing (per-response max_tokens is independent per edit; one giant write hits the cap incl. thinking tokens) 2026-07-14 14:31:09 +01:00
Jesse Zhang 52996604bf turf-war prompt: write policy in one compact pass (no incremental rewrites, no giant tables) to avoid output-token-limit failures 2026-07-14 14:27:59 +01:00
Jesse Zhang 90500bb8d6 Register Sonnet 5 CC Max (卷地风); add precise root-cause diagnosis to underperformer notes (Terra/Opus-xhigh/Fable-high) 2026-07-14 13:52:28 +01:00
Jesse Zhang e215627e68 Register three Claude turf-war runs: Fable 5 CC High, Opus 4.8 CC Max/xhigh (self-named) 2026-07-14 12:40:01 +01:00
Jesse Zhang 7d9dd07cc6 turf-war prompt: file-capable harnesses build the file incrementally (avoid single-output truncation on long policies); still no test runs 2026-07-14 12:04:12 +01:00
Jesse Zhang d3b92ccee8 turf-war: Terra did self-name — register agentName 拓荒狐 2026-07-14 03:46:13 +01:00
Jesse Zhang 2a024a9dc8 Register three turf-war runs: GPT-5.6-Sol (Codex CLI max/xhigh), GPT-5.6-Terra (Codex CLI xhigh)
Policies stay private per case rules; maintainer-executed one-shot runs.
2026-07-14 03:34:46 +01:00
Jesse Zhang ce9fd8bafe turf-war prompt: opponents are other Agents (model x harness), not 'AI models' 2026-07-14 03:19:40 +01:00
Jesse Zhang 43a70bd651 turf-war prompt: maintainer-filled [This run] line (model x harness x effort, target filename) 2026-07-14 03:09:38 +01:00
Jesse Zhang 9cd85bad21 turf-war prompt: deliver a file (save turf-war.js in file-capable harnesses, print content otherwise) 2026-07-14 03:07:30 +01:00
Jesse Zhang 5c2a55bbb2 turf-war prompt: agents name themselves (fun name, <=5 chars zh / one short word en) 2026-07-14 03:00:28 +01:00
Jesse Zhang 379ab28279 turf-war prompt: forbid web search / skills / external tools / test runs (world-knowledge only) 2026-07-14 02:55:04 +01:00
Jesse Zhang 6dccc35cd8 Turf War is maintainer-run: no artifact PRs, policies stay private (anti-scouting); README case list updated to five cases 2026-07-14 02:50:27 +01:00
Jesse Zhang 50fb9978dc Add case 05 Turf War (kind: agent) + agent-case contribution guide
One-shot JS policy agents battle head-to-head on a 40x40 grid; ranked by
objective wins (Bradley-Terry), refereed server-side. Inspired by Jiayi
Weng's Learning Beyond Gradients.
2026-07-14 02:24:07 +01:00
Jesse ZhangandClaude Opus 4.8 e3a60756f9 chore: regroup registry order by vendor
GLM-5.1 -> 120 (beside GLM-5.2/Turbo), DeepSeek V4 Flash -> 90.5 (beside V4-Pro), Nex-AGI -> 65 (out of the xAI block).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-14 00:08:28 +01:00
Jesse ZhangandClaude Opus 4.8 cbfce3b7cc feat: add cs-dust2 React case with two model takes + react kind support
New case cs-dust2 (kind:react): a from-scratch React + three.js 5v5 Dust2 FPS.
Two takes registered: Claude Fable 5 / Claude Code / High (with a hand fix for a
64Hz fixed-step firing bug on high-refresh displays) and Claude Opus 4.8 /
Claude Code / Max (dust2-arena, one-shot). React cases commit source only; the
single file is built from source at deploy time. validate-data.ts now accepts a
React project directory as the declared artifact. AGENTS.md rewritten
English-only with React-case, bare-harness (no skills/plugins) and
artifact-anonymity rules.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-14 00:08:28 +01:00
Jesse ZhangandClaude Opus 4.8 5d52843621 fix: order GPT-5.5 Pro below GPT-5.6 (newest-first within OpenAI)
GPT-5.5 Pro sat at order 20, above the GPT-5.6 entries, breaking the
newest-first grouping used elsewhere. Move it to 29.8 so the OpenAI block
reads 5.6 -> 5.5 -> 5.4 -> 5.3 -> 5.2.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-10 00:37:57 +01:00
Jesse ZhangandClaude Opus 4.8 b8ed871bc0 docs: document multi-take variant arrays in AGENTS.md
Explain when runs.<case> becomes an array (same model x harness x effort,
several takes), the distinct-descriptive-file rule, the index.html trap,
and per-variant contributor.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-09 23:09:15 +01:00
Jesse ZhangandClaude Opus 4.8 64609bd6c8 feat: add GPT-5.6-Terra and alternate takes for GPT-5.6-Sol
New model gpt-5-6-terra (Codex CLI, ultra): mythos-craft, pelican-cycling,
skeleton-watch (one-shot, unmodified).

gpt-5-6-sol-ultra gains alternate one-shot variants for existing cases:
mythos-craft 'Block Era', two more pelican SVGs, and a cleanly completed
skeleton-watch 'Calibre 01' kept alongside the interruption-recovered
AURELIUS S-01. Extra variants attributed to Nagi-ovo.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-09 23:09:15 +01:00