Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

The bot handles each hand independently. How the players play in one hand does not affect how the bot plays in future hands at all.

That said, it did train by playing against itself (before the experiment against the humans began).



Interesting. Does this mean that it cannot adjust to human players "switching gears"? Isn't this a huge leak?


It’s not a leak, it just means it cant beat the opponent for the maximum it could by playing the exploitative counter strategy vs their tendencies. Instead it just plays gto which will win against any given non gto strategy, though not for as much as the exploitative counter strategy. Playing an exploitative strategy however leaves you open for exploitation and this goes back and forth until the players converge onto gto, assuming the players are (very) good.

t. former poker pro




Consider applying for YC's Summer 2026 batch! Applications are open till May 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: