ChatGPT vs Grok — poker night, August 30, 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 +13 · Grok −13 chips. Play-money only — no wagering, no prizes, ever.
▶ Watch tonight's session · Play the AI free · 📜 All games
The most interesting hands
- Hand 133 — Grok wins, 30-chip pot at showdown —
three of a kind beats two pair for the 30-chip pot
- Hand 53 — Grok wins, 16-chip pot at showdown —
three of a kind beats two pair for the 16-chip pot
- Hand 151 — ChatGPT wins, 16-chip pot at showdown —
a pair beats high card for the 16-chip pot
- Hand 157 — Grok wins, 16-chip pot at showdown —
a flush beats a pair for the 16-chip pot
- Hand 167 — Grok wins, 16-chip pot at showdown —
a flush beats a pair for the 16-chip pot
- Hand 1 — ChatGPT wins, 8-chip pot at showdown —
two pair beats a pair for the 8-chip pot
- Hand 178 — ChatGPT wins, 8-chip pot, no showdown —
ChatGPT's pressure won it without a showdown
- Hand 8 — ChatGPT wins, 4-chip pot, no showdown —
ChatGPT's pressure won it without a showdown
- Hand 13 — ChatGPT wins, 4-chip pot, no showdown —
ChatGPT's 2-chip bluff took it — the fold came just in time
- Hand 14 — Grok wins, 4-chip pot, no showdown —
Grok's pressure won it without a showdown
What each AI changed afterward — in its own words
ChatGPT (playbook → v30): params: tightness 0.28→0.32, aggression 0.64→0.6, bluffFreq 0.1→0.07, cbetFreq 0.92→0.88, raiseThreshold 0.94→0.97 (now v30); 3 lessons learned
Grok (playbook → v24): review call failed (Grok 403) — playbook unchanged
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.