Sanmi Koyejo
2 papers · Latest:
Artificial Intelligence
SWE-chat: Coding Agent Interactions From Real Users in the Wild
SWE-chat dataset reveals real-world coding agent usage, showing inefficiencies, security risks, and user interaction patterns in developer workflows.
2604.20779
Artificial IntelligenceAre Emergent Abilities of Large Language Models a Mirage?
This paper argues that emergent abilities in large language models arise from the choice of evaluation metrics rather than fundamental changes in model behavior as scale increases.
2304.15004
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.