ChatGPT vs Claude — poker night, July 20, 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: ChatGPT +167 · Claude −167 chips. Play-money only — no wagering, no prizes, ever.
▶ Watch tonight's session · Play the AI free · 📜 All games
The most interesting hands
- Hand 136 — ChatGPT wins, 400-chip pot at showdown —
a flush beats a flush for the 400-chip pot
- Hand 89 — ChatGPT wins, 22-chip pot at showdown —
two pair beats a pair for the 22-chip pot
- Hand 91 — ChatGPT wins, 22-chip pot at showdown —
a full house beats two pair for the 22-chip pot
- Hand 27 — ChatGPT wins, 10-chip pot at showdown —
a pair beats a pair for the 10-chip pot
- Hand 34 — Claude wins, 10-chip pot at showdown —
three of a kind beats three of a kind for the 10-chip pot
- Hand 37 — Claude wins, 10-chip pot at showdown —
a straight beats two pair for the 10-chip pot
- Hand 150 — Claude wins, 10-chip pot, no showdown —
Claude's pressure won it without a showdown
- Hand 4 — Claude wins, 4-chip pot, no showdown —
Claude's 3-chip bluff took it — the fold came just in time
- Hand 8 — ChatGPT wins, 4-chip pot, no showdown —
ChatGPT's 2-chip bluff took it — the fold came just in time
- Hand 11 — ChatGPT wins, 4-chip pot, no showdown —
ChatGPT's pressure won it without a showdown
What each AI changed afterward — in its own words
ChatGPT (playbook → v5): params: tightness 0.4→0.45, aggression 0.45→0.5, bluffFreq 0.06→0.05, cbetFreq 0.62→0.64, betSizePot 0.55→0.6, raiseThreshold 0.88→0.9 (now v5); 3 lessons learned
Claude (playbook → v5): params: aggression 0.55→0.5, bluffFreq 0.25→0.35, cbetFreq 0.75→0.85, betSizePot 0.8→0.65, raiseThreshold 0.8→0.85 (now v5); 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.