How many large language models do you need to write code without errors? - Anastasiia Grishina

What’s stopping software developers writing better code, with all the tools available today? Discover how our research group is addressing this by using multiple language models to generate, debug and repair code. Our framework reduces bugs, improves test pass rates and aims to make quality coding accessible to everyone.
Taking place at AI UK, PitchFest participants have 90 seconds to engage the crowd and panel by making their work accessible and highlighting its real-world impacts, creativity and innovation.
Judges:
Mark Girolami - Chief Scientist, The Alan Turing Institute
Trias Gkikopoulos - Innovation Lead, Innovate UK
Maria Delgado Ortet - PhD Student, University of Cambridge
Gavin Stephenson - Managing Director, Accenture
See more from AIUK: / @ai_uk