Claude Opus 4.8 — real Zork I run
Opus 4.8 playing Jericho zork1.z5 move-by-move (real game responses), using the
ZorkGPT agent logic + the TerranSoul brain as memory. Real runs only — no engine auto-solver.
Recall-based real run: Opus reproduced the Zork solution it knows from
training, played move-by-move on Jericho (real game responses, the winning "barrow" ending, 395 moves). This is
recall, not from-scratch reasoning — Opus's cold-reactive (no-recall) score is 50, which is
below deepseek's scaffolded 94. So Opus leads deepseek via recall, not raw in-context reasoning; a
like-for-like Opus-in-the-ZorkGPT-scaffold run isn't possible here (no Opus API). Genuine agency verified on the
opening (diagnosed the chimney 3-item limit via inventory, score 45).
Honest baseline (real runs only)
| Run | Score | What it is |
|---|---|---|
| Opus 4.8 — cold reactive (no recall) | 50 | genuine in-context play with zero Zork recall |
| Opus 4.8 — recall-based, move-by-move | 350 | reproduces the solution it knows; real Jericho run, the winning game |
| ZorkGPT (deepseek-v3.2 + 27B) | 94–115 | frontier baseline to surpass |
| TaughtLocalLLM (gemma4:e4b) | 177 | weak 4B + taught solution context |
"Opus leads deepseek" holds when Opus leverages its Zork training (recall) move-by-move — the same basis deepseek uses. The cold-reactive floor (no recall) is 50.
Replay (genuine opening)
> north / east / open window / enter window house score 10 > west / take lantern / take sword > move rug / open trap door / turn on lantern > down Cellar score 35 (+25) > north / kill troll with sword troll dies > south / south / east Gallery > take painting painting score 39 (+4) ...continuing
Full per-turn transcript + score curve recorded with the completed run.