Hacker Newsnew | past | comments | ask | show | jobs | submit | projectyang's commentslogin

Yep, I used claude code to help build this.

Each hand is stateless

Yes, the prompt tries to get them to play GTO. I do think their preflop play is the closest to mirroring this compared to postflop behavior.

Is this tuned to tournament or cash GTO? To the OP's shock about pocket 4's (I think this is what they meant by 4-pair(?)), folding 4's pre flop in early position to no raise would be fairly standard in tournament GTO (although the stage of the tournament and # BBs can change things up significantly), but less standard for sure in cash (almost never probably).

On mobile I had to squeeze the names, but on a wider view you'll see that it's Claude (Opus 4.5) and Claude (Sonnet 4.5).

Nope, no external poker libraries. Just a basic nodejs and socket.io server with game logic.

Cool

While others have commented about solvers, I'd also like to bring up AI poker bots such as Pluribus (https://en.wikipedia.org/wiki/Pluribus_(poker_bot)).

This also wouldn't even be a close contest, I think Pluribus demonstrated a solid win rate against professional players in a test.

As I was developing this project, a main thought came to mind as to the comparison between cost and performance between a "purpose" built AI such as Pluribus versus a general LLM model. I think Pluribus training costs ~$144 in cloud computing credits.


Should be noted that this bot is heads up only? I believe a form of heads up poker is effectively solved as well-- limit hold'em heads up

For my implementation, I'm passing in the current hand's action history (e.g. Player 1 raises to $X preflop, Player 2 calls, Player 3 calls. Flop is A B C, Player 2 checks, etc) whenever the action is on the player.

Your idea of having it being passed in real time and having the LLM create a chain of thoughts even if action is not on them is interesting. I'd be curious to see if it would result in improved play.


Good question! The player rooms have a rate limit per day. And as for the main table, it's actually a replay of hands I recorded the LLMs playing against each other over an extended time which eventually loops.

I'm actually surprised at how well they play pre-flop (mostly). Did some initial analysis on VPIP/PFR across positions, and somewhat decent.

Post-flop on the other hand is all over the place...


there plenty of published preflop charts and GTO ranges

in fact, a fun project would be take a non-reasoning model, play on a lesser known game format, and see if it learns an "a ha" moment or explicitly simulate moves ahead


The bot you're playing is outdated compared to modern ones. Within the last few years, there's been a lot of research done similar to what we saw with AlphaGo: https://en.wikipedia.org/wiki/Pluribus_(poker_bot).

You may also enjoy diving into academic papers related to modern game theory for No Limit Paper. That's the current meta these days for high-level competitive play (last time I checked).


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

Search: