University of Cambridge > Talks.cam > Artificial Intelligence Research Group Talks (Computer Laboratory) > Success, sensitivity and unbelievable quality of LLM code generation

Log in

University Account

External (via Google)

Information on

Subscribing to talks details

Finding a talk details

Adding a talk details

Disseminating talks details

Help and Documentation details

Success, sensitivity and unbelievable quality of LLM code generation

Download to your calendar using vCal

Andrei Paleyes (University of Cambridge)
Tuesday 24 June 2025, 13:00-14:00
Lecture Theatre 2, Computer Laboratory, William Gates Building.

If you have a question about this talk, please contact Mateja Jamnik .

Code generation is one of the most active areas of application of Large Language Models (LLMs). LLMs lower barriers to writing code and accelerate development process, so much so there are now research projects and businesses powered largely by LLM code generation process. It is however important to realise that the overall quality of generated programs depends on the quality of given prompts. Functionality and quality of generated code can be sensitive to user’s background and familiarity with software engineering.

In this talk we will discuss several aspects of LLM code generation. We will talk about end-user software engineering paradigm and how it is put to practice today. We will investigate how sensitive this approach can be to changes in the requirements. And we will see how LLMs can be deceptively good at solving seemingly impossible problems with code.

You can also join us on Zoom

This talk is part of the Artificial Intelligence Research Group Talks (Computer Laboratory) series.