BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Success\, sensitivity and unbelievable quality of LLM code generat
 ion - Andrei Paleyes (University of Cambridge)
DTSTART:20250624T120000Z
DTEND:20250624T130000Z
UID:TALK232729@talks.cam.ac.uk
CONTACT:Mateja Jamnik
DESCRIPTION: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 project
 s and businesses powered largely by LLM code generation process. It is how
 ever important to realise that the overall quality of generated programs d
 epends on the quality of given prompts. Functionality and quality of gener
 ated code can be sensitive to user's background and familiarity with softw
 are engineering.\n\nIn this talk we will discuss several aspects of LLM co
 de generation. We will talk about end-user software engineering paradigm a
 nd 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
 .\n\n"You can also join us on Zoom":https://cam-ac-uk.zoom.us/j/8340033552
 2?pwd=LkjYvMOvVpMbabOV1MVTm8QU6DrGN7.1\n
LOCATION:Lecture Theatre 2\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR