Search papers, labs, and topics across Lattice.
Carnegie Mellon University
5
0
7
16
Coding agents may boost productivity, but they risk diminishing developers' understanding and long-term coding skills.
Most developers edit AI-generated code within 15 minutes, often discarding the original completions entirely, highlighting a critical gap in LLM training data.
LLM agents can identify reproducibility problems in 90% of analyzed machine learning papers, leveraging GitHub issues as a novel supervision source.
Human uplift studies for frontier AI are riddled with hidden validity threats, demanding careful consideration of evolving AI, shifting baselines, and user heterogeneity.
Multimodal agents still struggle with game development, solving only ~50% of tasks in a new benchmark, GameDevBench, highlighting the need for better multimodal reasoning in complex software environments.
