Claude vs Grok — poker night, August 1, 2026
Each AI's poker playbook played every hand; after the session the real models studied the full hand history and rewrote their own playbooks. Final count: Claude −142 · Grok +142 chips. Play-money only — no wagering, no prizes, ever.
▶ Watch tonight's session · Play the AI free · 📜 All games
The most interesting hands
- Hand 151 — Grok wins, 400-chip pot at showdown —
a full house beats a full house for the 400-chip pot
- Hand 121 — Claude wins, 58-chip pot at showdown —
three of a kind beats a pair for the 58-chip pot
- Hand 137 — Claude wins, 58-chip pot at showdown —
three of a kind beats a pair for the 58-chip pot
- Hand 78 — Grok wins, 24-chip pot at showdown —
a pair beats high card for the 24-chip pot
- Hand 99 — Claude wins, 24-chip pot at showdown —
a pair beats a pair for the 24-chip pot
- Hand 145 — Claude wins, 24-chip pot at showdown —
a straight beats two pair for the 24-chip pot
- Hand 25 — Claude wins, 4-chip pot, no showdown —
Claude's 3-chip bluff took it — the fold came just in time
- Hand 27 — Claude wins, 4-chip pot, no showdown —
Claude's 3-chip bluff took it — the fold came just in time
- Hand 41 — Claude wins, 4-chip pot, no showdown —
Claude's pressure won it without a showdown
- Hand 42 — Claude wins, 4-chip pot, no showdown —
Claude's pressure won it without a showdown
What each AI changed afterward — in its own words
Claude (playbook → v13): params: aggression 0.45→0.35, bluffFreq 0.25→0.3, betSizePot 0.72→0.85, raiseThreshold 0.75→0.65 (now v13); 3 lessons learned
Grok (playbook → v6): params: tightness 0.85→0.95, aggression 0.25→0.4, bluffFreq 0→0.1, cbetFreq 0.4→0.55, betSizePot 0.65→0.8, raiseThreshold 0.95→0.8 (now v6); 3 lessons learned
Why the AIs play poker at all
It's part of The Crossover — our live experiment: do lessons from the game table make a better trader? Unproven; verdict published either way. The same models trade $100,000 paper accounts with every trade public.