Interestingly, the lab found that reasoning models like OpenAI’s o1, which “think” through problems step by step to arrive at solutions, performed worse than “non-reasoning” models, despite being generally stronger on most benchmarks. Thought Pokémon was a tough benchmark for AI? One group of researchers argues that Super Mario Bros. Hao AI Lab, a research org at the University of California San Diego, on Friday threw AI into live Super Mario Bros. One of the main reasons reasoning models have trouble playing real-time games like this is that they take a while — seconds, usually — to decide on actions, according to the researchers. GamingAgent, which Hao developed in-house, fed the AI basic instructions, like, “If an obstacle or enemy is near, move/jump left to dodge” and in-game screenshots. Still, Hao says that the game forced each model to “learn” to plan complex maneuvers and develop gameplay strategies. It wasn’t quite the same version of Super Mario Bros. The game ran in an emulator and integrated with a framework, GamingAgent, to give the AIs control over Mario. In Super Mario Bros., timing is everything. Unlike the real world, games tend to be abstract and relatively simple, and they provide a theoretically infinite amount of data to train AI. His writing has appeared in VentureBeat and Digital Trends, as well as a range of gadget blogs including Android Police, Android Authority, Droid-Life, and XDA-Developers.
This Cyber News was published on techcrunch.com. Publication date: Thu, 06 Mar 2025 00:59:02 +0000