PurpCode UIUC

Rule Learning: teaching LLMs secure coding rules and general safety practices
Reinforcement Learning: letting LLMs co-exercise their safety and utility via verifiable tasks

non-profit

🥇 Winner Defender Team at Amazon Nova AI Challenge 2025

oceandrifters published a dataset about 2 months ago

oceandrifters published a dataset about 2 months ago

zhewang updated a dataset 2 months ago

purpcode 's models 4