Using LLMs for safe low-level programming | Microsoft Research Forum

7 882
50.5
Опубликовано 25 февраля 2025, 19:09
Aseem Rastogi, Principal Researcher, and Pantazis Deligiannis, Principal Research Engineer from Microsoft Research FoSSE (Future of Scalable Software Engineering) discuss the technical results from ICSE'2025 on using Large Language Models (LLMs) for safe low-level programming. The results demonstrate LLMs inferring machine-checkable memory safety invariants in legacy C code, and how LLMs assist in fixing compilation errors in Rust codebases.

This session aired on February 25, 2025, at Microsoft Research Forum, Episode 5.

Register for the series: aka.ms/registerresearchforumYT...

Continue watching episode 5: aka.ms/researchforumYTe5
Explore all previous episodes: aka.ms/researchforumYTplaylist
автотехномузыкадетское