ChatGPT vs Claude — poker night, August 5, 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 −10 · Claude +10 chips. Play-money only — no wagering, no prizes, ever.
▶ Watch tonight's session · Play the AI free · 📜 All games
The most interesting hands
- Hand 167 — ChatGPT wins, 76-chip pot at showdown —
two pair beats a pair for the 76-chip pot
- Hand 59 — ChatGPT wins, 28-chip pot at showdown —
a pair beats a pair for the 28-chip pot
- Hand 87 — Claude wins, 22-chip pot at showdown —
a straight beats high card for the 22-chip pot
- Hand 149 — ChatGPT wins, 18-chip pot at showdown —
a flush beats a pair for the 18-chip pot
- Hand 161 — ChatGPT wins, 18-chip pot at showdown —
a flush beats two pair for the 18-chip pot
- Hand 22 — Claude wins, 10-chip pot, no showdown —
Claude's 9-chip bluff took it — the fold came just in time
- Hand 38 — Claude wins, 10-chip pot at showdown —
a straight beats a pair for the 10-chip pot
- Hand 45 — Claude wins, 10-chip pot, no showdown —
Claude's pressure won it without a showdown
- Hand 130 — Claude wins, 10-chip pot, no showdown —
Claude's 9-chip bluff took it — the fold came just in time
- Hand 157 — Claude wins, 10-chip pot, no showdown —
Claude's pressure won it without a showdown
What each AI changed afterward — in its own words
ChatGPT (playbook → v15): params: tightness 0.38→0.32, aggression 0.68→0.77, bluffFreq 0.08→0.1, cbetFreq 0.68→0.62, betSizePot 0.58→0.6, raiseThreshold 0.96→0.9 (now v15); 3 lessons learned
Claude (playbook → v16): params: bluffFreq 0.4→0.28, cbetFreq 0.85→0.75, betSizePot 0.85→0.95 (now v16); 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.