Palisade Research recently detailed a ChatGPT experiment in which a reasoning model was told to play chess against a more powerful opponent and win. Rather than attempt to beat the stronger opponent, ChatGPT o1 tried to hack the system. This forced the opponent to concede the game, and the AI achieved its goal.
Fast-forward to mid-February and Palisade Research has published its full study, which looked at cheating behavior from AI programs like ChatGPT and some of its top rivals. The conclusions were similar, with a big twist. It turns out that reasoning AIs like ChatGPT o1-preview and DeepSeek R1 are more likely to cheat when they think they might be losing.
The post AI like ChatGPT o1 and DeepSeek R1 might cheat to win a game appeared first on BGR.
Today’s Top Deals
Today’s deals: $149 AirPods 4 with ANC, 20% off Crest 3D White toothpaste, $18 Roku Express, more
Best deals: Tech, laptops, TVs, and more sales
Presidents’ Day weekend deals: $298 Nintendo Switch OLED, $279 Apple iPad 10, Dell & HP laptops, more
Best Fire TV Stick deals for February 2025
AI like ChatGPT o1 and DeepSeek R1 might cheat to win a game originally appeared on BGR.com on Thu, 20 Feb 2025 at 13:13:00 EDT. Please see our terms for use of feeds.