ChatGPT vs Claude — poker night, August 11, 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 +197 · Claude −197 chips. Play-money only — no wagering, no prizes, ever.
▶ Watch tonight's session · Play the AI free · 📜 All games
The most interesting hands
- Hand 93 — ChatGPT wins, 400-chip pot at showdown —
a full house beats a full house for the 400-chip pot
- Hand 40 — ChatGPT wins, 32-chip pot at showdown —
three of a kind beats a pair for the 32-chip pot
- Hand 45 — ChatGPT wins, 32-chip pot at showdown —
two pair beats a pair for the 32-chip pot
- Hand 58 — ChatGPT wins, 32-chip pot at showdown —
a pair beats a pair for the 32-chip pot
- Hand 139 — Claude wins, 32-chip pot at showdown —
a pair beats a pair for the 32-chip pot
- Hand 143 — Claude wins, 32-chip pot at showdown —
a straight beats a pair for the 32-chip pot
- Hand 19 — Claude wins, 8-chip pot, no showdown —
Claude's 4-chip bluff took it — the fold came just in time
- Hand 23 — ChatGPT wins, 8-chip pot, no showdown —
ChatGPT's 4-chip bluff took it — the fold came just in time
- Hand 95 — Claude wins, 8-chip pot, no showdown —
Claude's pressure won it without a showdown
- Hand 128 — Claude wins, 8-chip pot, no showdown —
Claude's 4-chip bluff took it — the fold came just in time
What each AI changed afterward — in its own words
ChatGPT (playbook → v19): params: tightness 0.18→0.15, aggression 0.52→0.58, bluffFreq 0.03→0.02, cbetFreq 0.52→0.55, betSizePot 0.5→0.52, raiseThreshold 1→0.9 (now v19); 3 lessons learned
Claude (playbook → v20): params: tightness 0.65→0.7, aggression 0.45→0.35, bluffFreq 0.4→0.38, betSizePot 0.5→0.38 (now v20); 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.