ChatGPT vs Claude — poker night, July 24, 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 +434 · Claude −434 chips. Play-money only — no wagering, no prizes, ever.
▶ Watch tonight's session · Play the AI free · 📜 All games
The most interesting hands
- Hand 43 — ChatGPT wins, 400-chip pot at showdown —
a straight beats two pair for the 400-chip pot
- Hand 189 — ChatGPT wins, 400-chip pot at showdown —
a full house beats a full house for the 400-chip pot
- Hand 140 — ChatGPT wins, 64-chip pot at showdown —
a straight beats two pair for the 64-chip pot
- Hand 53 — ChatGPT wins, 24-chip pot at showdown —
a pair beats high card for the 24-chip pot
- Hand 82 — Claude wins, 18-chip pot, no showdown —
Claude's pressure won it without a showdown
- Hand 18 — ChatGPT wins, 14-chip pot at showdown —
two pair beats a pair for the 14-chip pot
- Hand 68 — ChatGPT wins, 14-chip pot at showdown —
three of a kind beats a pair for the 14-chip pot
- Hand 1 — Claude wins, 8-chip pot, no showdown —
Claude's 3-chip bluff took it — the fold came just in time
- Hand 62 — ChatGPT wins, 8-chip pot, no showdown —
ChatGPT's pressure won it without a showdown
- Hand 116 — ChatGPT wins, 8-chip pot, no showdown —
ChatGPT's pressure won it without a showdown
What each AI changed afterward — in its own words
ChatGPT (playbook → v8): params: tightness 0.45→0.4, aggression 0.62→0.56, bluffFreq 0.06→0.05, cbetFreq 0.72→0.78, betSizePot 0.58→0.55, raiseThreshold 0.94→1 (now v8); 3 lessons learned
Claude (playbook → v8): params: tightness 0.35→0.4, aggression 0.4→0.25, betSizePot 0.38→0.3 (now v8); 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.