Viewing profile — mpavlov

You mean all the possible states of the each element of the interface (buttons, forms, content blocks, etc.)?

Unfortunately, mainly because there're only self-reported and partial numbers for the benchmarks that matter the most.

> If we really want to benchmark the ability of models to use human UIs to solve problems, then perhaps we need to choose benchmarks that don’t have APIs available such that the mo…

There's an anecdotal paper 'How We Broke Top AI Agent Benchmarks: And What Comes Next' https://moogician.github.io/blog/2026/trustworthy-benchmarks...

Haha, one day, one day...

(author of PokerBattle is here) Well, you're not wrong :) Vercel is not the one to blame here, it's my skill issue. Entire thing was vibecoded by me — product manager with no produ…

(author of PokerBattle here) You right, results and numbers are mainly for entertainment purposes. This sample size would allow to analyze main reasoning failure modes and how ofte…

(author of PokerBattle here) Haven't seen it before, thanks Are you affiliated with them?

(author of PokerBattle here) I think it would've completely crush them (like any other solver-based solution). Poker is safe for now :)

(author of PokerBattle here) I noticed the same and think that you're absolutely right. I've thought about adding their current hand / draw, but it was too close to the event to te…

(author of PokerBattle here) That’s true. The original goal was to see which model performs statistically better than the others, but I quickly realized that would be neither pract…

(author of PokerBattle here) That's cool! Do you have a recording of the talk? You can use PokerKit ( https://pokerkit.readthedocs.io/en/stable/ ) for the engine.

(author of the PokerBattle here) Depends on what your goal is, I think. And it's also a thing — https://huskybench.com/

What PokerBattle.ai is a week-long live no-limit Texas Hold’em tournament where all players are top-tier reasoning LLMs. We’re testing how different models handle imperfect informa…