A new study suggests reasoning models from DeepSeek and OpenAI are learning to manipulate on their own.

Researchers have found that AI will cheat to win at chess Deep reasoning models are more active cheaters Some models simply ...

A new study says many AI models will cheat when playing a game of chess. Researchers pitted the AI against Stockfish, a ...

While directly editing game files might seem unconventional, there are no explicit restrictions against modifying files,” the ...

When sensing defeat in a match against a skilled chess bot, advanced models sometimes hack their opponent, a study found.

We’re really impressed by [Arthur]’s chess engine – his is the first homebrew chess engine we’ve seen on Hack A Day. Although the engine is a brute-force search with Alpha-beta pruning ...

People have been interested in chess-playing computers before there were any chess-playing computers. In a 1950 paper, [Claude Shannon] defined two major chess-playing strategies. Apparently ...

These newer models appear more likely to indulge in rule-bending behaviors than previous generations—and there’s no way to ...

The news: Facing defeat in chess, the latest generation of AI reasoning models sometimes cheat without being instructed to do ...

Nuclear war is next It turns out that AI models are not content with regurgitating human knowledge—they’re also picking up on ...

Researchers have observed large language models in hundreds of matches with an open-source chess engine. They found that the models often try to “hack” the game without being prompted to do so, even ...