Poker Tournament for LLMs

Re:Poker Tournament for LLMs by furyofantares on Tuesday October 28, 2025 @01:59PM (#45736423)

> 3) LLMs do not have a mechanism for sampling from given probability distributions. E.g. if you ask LLM to sample a random number from 1 to 10, it will likely give you 3 or 7, as those are overrepresented in the training data.

You can have them output a probability distribution and then have normal code pick the action. There's other ways to do this, you don't need to make the LLM pick a random number.

[ Parent | on HN ]

Re:Poker Tournament for LLMs by Nicook on Tuesday October 28, 2025 @02:25PM (#45736788)

so you're confirming that what he said is correct

[ Parent | on HN ]

Re:Poker Tournament for LLMs by furyofantares on Tuesday October 28, 2025 @02:43PM (#45737003)

No.

It's not like an LLM can play poker without some shim around it. You're gonna have to interpret its results and take actions. And you want the LLM to produce a distribution either way before picking an explicit action from that distribution. Having the shim pick the random number instead of the LLM does not take anything away from it.

[ Parent | on HN ]