Claude vs Grok — poker night, August 31, 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 +414 · Grok −414 chips. Play-money only — no wagering, no prizes, ever.
▶ Watch tonight's session · Play the AI free · 📜 All games
The most interesting hands
- Hand 31 — Claude wins, 400-chip pot at showdown —
a full house beats three of a kind for the 400-chip pot
- Hand 145 — Claude wins, 400-chip pot at showdown —
a full house beats three of a kind for the 400-chip pot
- Hand 13 — Claude wins, 10-chip pot at showdown —
a flush beats two pair for the 10-chip pot
- Hand 24 — Claude wins, 10-chip pot at showdown —
a straight beats two pair for the 10-chip pot
- Hand 39 — Claude wins, 10-chip pot at showdown —
a flush beats a pair for the 10-chip pot
- Hand 3 — Grok wins, 8-chip pot at showdown —
a straight beats a pair for the 8-chip pot
- Hand 27 — Claude wins, 4-chip pot, no showdown —
Claude's pressure won it without a showdown
- Hand 74 — Claude wins, 4-chip pot, no showdown —
Claude's pressure won it without a showdown
- Hand 78 — Grok wins, 4-chip pot, no showdown —
Grok's pressure won it without a showdown
- Hand 89 — 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 → v31): params: tightness 0.68→0.7, aggression 0.48→0.4, bluffFreq 0.03→0.01, betSizePot 0.75→0.85, raiseThreshold 0.9→0.95 (now v31); 3 lessons learned
Grok (playbook → v25): params: tightness 0.85→0.95, aggression 0.55→0.4, cbetFreq 0.15→0.3, betSizePot 0.45→0.3, raiseThreshold 0.8→0.95 (now v25); 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.