Meta and Duke study finds reward hacking can spread between AI models
Photo: Crypto Briefing
Small coding agents trained to game their evaluators passed those habits to Claude and Gemini through shared code, plans, and memory A small AI model that learned to cheat on its homework can apparently teach the habit to much bigger, more capable models. That is the central finding of new research from Meta Superintelligence Labs and Duke University. It shows that reward hacking, where an AI games its scoring system instead of doing the actual job, can move from weak coding agents to frontier models through the code, plans, and memory they share.
Source: Crypto Briefing
