The game of checkers has roughly 500 billion billion possible positions (5 × 1020). The task of solving the game, determining the final result in a game with no mistakes made by either player, is daunting. Since 1989, almost continuously, dozens of ...
Look-ahead Reasoning with a Learned Model in Imperfect Information Games
Test-time reasoning significantly enhances pre-trained AI agents' performance. However, it requires an explicit environment model, often unavailable or overly complex in real-world scenarios....
Ante: A New Way to Blend Borrow Checking and Reference Counting
Ante has taken the first step towards something we all thought was impossible: blending reference counting and borrow checking without run-time crashes. 0
AI Has Ruined the Job Market
Maybe flawed people were better than brute algorithms.
17. A Value for n-Person Games
17. A Value for n-Person Games was published in Contributions to the Theory of Games, Volume II on page 307.
Solving a Million-Step LLM Task with Zero Errors
LLMs have achieved remarkable breakthroughs in reasoning, insights, and tool use, but chaining these abilities into extended processes at the scale of those routinely executed by humans,...
Magic: The Gathering is Turing Complete
$\textit{Magic: The Gathering}$ is a popular and famously complicated trading card game about magical combat. In this paper we show that optimal play in real-world $\textit{Magic}$ is at least as...
Noam Brown on Twitter / X
And yes we did try other major problems without success. Sadly no Millennium Prize problems (yet).But also, we didn’t spend a lot on each problem. It’s possible to push test-time compute much further.— Noam Brown (@polynoamial) August 1, 2026
Integrity games: an online teaching tool on academic integrity for undergraduate students
In this paper, we introduce Integrity Games (https://integgame.eu/) – a freely available, gamified online teaching tool on academic integrity. In addition, we present results from a randomized controlled experiment measuring the learning outcomes from playing Integrity Games.
Asymmetry of verification and verifier’s rule — Jason Wei
Asymmetry of verification is the idea that some tasks are much easier to verify than to solve. With reinforcement learning (RL) that finally works in a general sense, asymmetry of verification is becoming one of the most important ideas in AI. Understanding asymmetry of verification th
OpenPoke: Recreating Poke's Architecture
How Poke's orchestrated multi-agent system works, what OpenPoke replicates, and the lessons for builders shipping AI assistants.
#Exploration: A Study of Count-Based Exploration for Deep...
Count-based exploration algorithms are known to perform near-optimally when used in conjunction with tabular reinforcement learning (RL) methods for solving small discrete Markov decision...
#checkmate is live. Multiplayer chess built 100% on the ATmosphere. No central database, all moves pulled in realtime from the firehose. Play at checkmate.blueate.blue #ATProto #chess
