The cheat code

Stephanie Arnet/MIT Technology Review | Adobe Stock, Envato

BRT has waxed poetic about AI as you, my loyal readers know. With this in mind, the smarter these entities get, the more deceitful they become as it seems cheating or hacking, as per us humans, is part of the equation becasue, after all, we created this tech, right?

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

The finding suggests that the next wave of AI models could be more likely to seek out deceptive ways of doing whatever they’ve been asked to do. And worst of all? There’s no simple way to fix it. 

Researchers from the AI research organization Palisade Research instructed seven large language models to play hundreds of games of chess against Stockfish, a powerful open-source chess engine. The group included OpenAI’s o1-preview and DeepSeek’s R1 reasoning models, both of which are trained to solve complex problems by breaking them down into stages.

The research suggests that the more sophisticated the AI model, the more likely it is to spontaneously try to “hack” the game in an attempt to beat its opponent. For example, it might run another copy of Stockfish to steal its moves, try to replace the chess engine with a much less proficient chess program, or overwrite the chess board to take control and delete its opponent’s pieces. Older, less powerful models such as GPT-4o would do this kind of thing only after explicit nudging from the team. The paper, which has not been peer-reviewed, has been published on arXiv. 

The researchers are concerned that AI models are being deployed faster than we are learning how to make them safe. “We’re heading toward a world of autonomous agents making decisions that have consequences,” says Dmitrii Volkov, research lead at Palisades Research.

The bad news is there’s currently no way to stop this from happening. Nobody knows exactly how—or why—AI models work the way they do, and while reasoning models can document their decision-making, there’s no guarantee that their records will accurately reflect what actually happened. Anthropic’s research suggests that AI models frequently make decisions based on factors they don’t explicitly explain, meaning monitoring these processes isn’t a reliable way to guarantee a model is safe. This is an ongoing area of concern for some AI researchers.

Thru a glass Darkly

In order for AI to interact with the real world in real time, it requires software writing software, which means … We don’t know how AI works because human programmers cannot write code in real-time in any way, shape or fashion.