A research study has found that AI reasoning models will sometimes cheat to win a game when it thinks it’s going to lose.

Students at UC Berkeley turned chatbot without reasoning capabilities into a “reasoning” one. This dramatically improved the ...

At the time of launch, OpenAI explained that Operator is powered by the Computer-Using Agent (CUA), which is a special AI ...

A new study has found that a few AI bots resort to hacking their opponent bots when they feel they're going to lose a game. Read on to know more.

Mini’s coding, math, and reasoning capabilities. Discover its strengths, limitations & real-world applications. This review ...

A 1B small language model can beat a 405B large language model in reasoning tasks if provided with the right test-time scaling strategy.

A Palisade Research study found that the newest reasoning models will cheat to win when tasked with defeating an advanced ...

GPT-4.5 could arrive as soon as next week, as Microsoft gets ready to host OpenAI’s latest models.

Reasoning models like ChatGPT o1 and DeepSeek R1 were found to cheat in games when they thought they were losing.

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