Search papers, labs, and topics across Lattice.
4
0
6
6
Pre-trained models in software projects aren't just libraries; they're sticky dependencies that accumulate over time and evolve based on capability, not just bug fixes.
Software developers are struggling to find the "Goldilocks zone" of AI reliance, and this framework offers a way to diagnose and address both over- and under-reliance on LLMs.
LLMs are overconfident in automated code revision, but fine-grained calibration can cut their miscalibration error by leveraging local edit decisions.
AI-generated code in open source gets a free pass: 80% of AI-co-authored pull requests from new contributors are merged without review, raising questions about code quality and security.
