Poker Tournament for LLMs

Post by RA_Fisher » Tue, Oct 28, 2025, 10:23 PM UTC

tarruda wrote: post #98

michalsustr wrote: post #31

I have PhD in algorithmic game theory and worked on poker. 1) There are currently no algorithms that can compute deterministic equilibrium strategies [0]. Therefore, mixed (randomized) strategies must be used for professional-level play or stronger. 2) In practice, strong play has been achieved with: i) online search and ii) a mechanism to ensure strategy consistency. Without ii) an adaptive opponent can learn to exp…

> LLMs do not have a mechanism for sampling from given probability distributions Would a LLM with tool calls be able to do this?

Post by hayd » Tue, Oct 28, 2025, 10:52 PM UTC

miggol wrote: post #5

I wonder if these will get better over time. Fun idea and I kind of want to join a table. For now at least, some can't even determine which hand they have: > LLAMA bets $170 on Flop > "We have top pair with Tc4d on a flop of 2s Ts Jh. The board is relatively dry, and we have a decent chance of having the best hand. We're betting $170.00 to build the pot and protect our hand." (That's not top pair)

Post by CamperBob2 » Tue, Oct 28, 2025, 11:01 PM UTC

mrob wrote: post #118

nostrebored wrote: post #113

Earlier quoted context omitted.

This is a poor conceptualization of how LLMs work. No implementations of models you’re talking to today are just raw autorrgressive predictors, taking the most likely next token. Most are presented with a variety of potential options and choose from the most likely set. A repeated hand and flop would not be played exactly the same in many cases (but a 27o would have a higher likelihood of being played the same way).

>No implementations of models you’re talking to today are just raw autorrgressive predictors, taking the most likely next token. Set the temperature to zero and that's exactly what you get. The point is the randomness is something applied externally, not a "core concept" for the LLM.

Post by ekropotin » Wed, Oct 29, 2025, 12:45 AM UTC

michalsustr wrote: post #31

I have PhD in algorithmic game theory and worked on poker. 1) There are currently no algorithms that can compute deterministic equilibrium strategies [0]. Therefore, mixed (randomized) strategies must be used for professional-level play or stronger. 2) In practice, strong play has been achieved with: i) online search and ii) a mechanism to ensure strategy consistency. Without ii) an adaptive opponent can learn to exp…

Post by mh- » Wed, Oct 29, 2025, 1:19 AM UTC

mh- wrote: post #188

frenzcan wrote: post #110

Earlier quoted context omitted.

I decided to try this: > sample a random number from 1 to 10 > ChatGPT: Here’s a random number between 1 and 10: 7 > again > ChatGPT: Your random number is: 3

that's pretty funny. > give me 11 random numbers in a set with range 1-10, allowing duplicates > ChatGPT: [3, 7, 1, 4, 9, 2, 6, 3, 10, 8, 5] I repeated it three times, 3 and 7 were always the first two elements haha. (I get why, and get why this is stupid to expect it to do, but it still gave me a laugh.)

  [random.randint(1, 10) for _ in range(11)]