ChatGPT vs Claude — poker night, July 27, 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 +129 · Claude −129 chips. Play-money only — no wagering, no prizes, ever.
▶ Watch tonight's session · Play the AI free · 📜 All games
The most interesting hands
- Hand 89 — ChatGPT wins, 128-chip pot at showdown —
a full house beats three of a kind for the 128-chip pot
- Hand 47 — Split pot, 92-chip pot at showdown —
chopped pot — both play a straight
- Hand 101 — ChatGPT wins, 44-chip pot at showdown —
a full house beats three of a kind for the 44-chip pot
- Hand 7 — ChatGPT wins, 20-chip pot at showdown —
a pair beats a pair for the 20-chip pot
- Hand 147 — ChatGPT wins, 20-chip pot at showdown —
two pair beats two pair for the 20-chip pot
- Hand 22 — ChatGPT wins, 18-chip pot, no showdown —
ChatGPT's pressure won it without a showdown
- Hand 172 — Claude wins, 18-chip pot at showdown —
a straight beats two pair for the 18-chip pot
- Hand 13 — Claude wins, 8-chip pot, no showdown —
Claude's 2-chip bluff took it — the fold came just in time
- Hand 37 — Claude wins, 8-chip pot, no showdown —
Claude's 2-chip bluff took it — the fold came just in time
- Hand 54 — Claude wins, 8-chip pot, no showdown —
Claude's 2-chip bluff took it — the fold came just in time
What each AI changed afterward — in its own words
ChatGPT (playbook → v10): params: tightness 0.5→0.51, aggression 0.64→0.66, bluffFreq 0.08→0.07, betSizePot 0.6→0.62, raiseThreshold 0.85→0.84 (now v10); 3 lessons learned
Claude (playbook → v10): params: tightness 0.35→0.5, bluffFreq 0.55→0.4, cbetFreq 1→0.85, betSizePot 0.3→0.45 (now v10); 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.