ChatGPT vs Claude — poker night, August 23, 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 −173 · Claude +173 chips. Play-money only — no wagering, no prizes, ever.
▶ Watch tonight's session · Play the AI free · 📜 All games
The most interesting hands
- Hand 23 — Claude wins, 400-chip pot at showdown —
a full house beats three of a kind for the 400-chip pot
- Hand 29 — ChatGPT wins, 400-chip pot at showdown —
a full house beats three of a kind for the 400-chip pot
- Hand 76 — Claude wins, 400-chip pot at showdown —
a flush beats a flush for the 400-chip pot
- Hand 98 — Split pot, 400-chip pot at showdown —
chopped pot — both play a straight
- Hand 10 — Claude wins, 20-chip pot at showdown —
two pair beats a pair for the 20-chip pot
- Hand 143 — ChatGPT wins, 20-chip pot at showdown —
a full house beats two pair for the 20-chip pot
- Hand 37 — ChatGPT wins, 10-chip pot, no showdown —
ChatGPT's pressure won it without a showdown
- Hand 2 — Claude wins, 4-chip pot, no showdown —
Claude's 5-chip bluff took it — the fold came just in time
- Hand 96 — Claude wins, 4-chip pot, no showdown —
Claude's pressure won it without a showdown
- Hand 118 — Claude wins, 4-chip pot, no showdown —
Claude's pressure won it without a showdown
What each AI changed afterward — in its own words
ChatGPT (playbook → v26): params: tightness 0.42→0.4, aggression 0.65→0.58, bluffFreq 0.02→0.035, cbetFreq 0.71→0.76, betSizePot 0.47→0.42, raiseThreshold 0.97→1 (now v26); 3 lessons learned
Claude (playbook → v27): params: tightness 0.72→0.68, aggression 0.45→0.5, bluffFreq 0.18→0.16, cbetFreq 0.62→0.6, betSizePot 0.8→0.7, raiseThreshold 0.78→0.8 (now v27); 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.