A new paper from Meta and Duke University shows that reward hacking in small coding agents can spread to stronger models
A paper from Meta and Duke University finds that reward hacking learned by small coding agents via RL can be propagated to stronger models reusing their work through passing code, plans, or shared memory.
Continue looking at this topic
OpportunitiesAfter half a year in Shengcai, how did a beginner earn 100,000+ with AI? ↗Hotly discussed viewsHow do you find the clearest wallpaper using an Agent, and how can you verify it is the original image? ↗Open-source projectThe AI Agent course covers 19 lessons and 4 practical projects. How can you learn enough to build one yourself? ↗News and AnalysisAI agents generated only hundreds of orders: how should we view DoorDash's pilot? ↗Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open AIHOT original