Name: Crafting Code Suggestions using Large Language Models
Start: 2022-10-25T11:00:00+02:00
End: 2022-10-25T12:00:00+02:00
Location: Room 522, Fantum

**Speaker**
Albert Ziegler

**Abstract**
By virtue of scale and clever architecture, large language models have made significant leaps in their ability to predict source code. That gives them potential. But turning that potential into actually useful tooling
requires overcoming a hard obstacle: Developers don't actually write source code. At least, not in the linear, every-file-for-itself fashion that can be predicted so successfully. Solving this challenge is shaping up to be a central question for AI-based developer tooling.

Using the example of GitHub Copilot, I'll give some insights into the strategies we used to address it for making code snippet suggestions. There, I'll mainly focus on promptcrafting for code, addressing:

* intra-file reordering,
* codebase linearization, and
* large-scale assessment.

**Bio**
Albert Ziegler ([https://githubnext.com/team/wunderalbert/](https://githubnext.com/team/wunderalbert/)) is a principal machine learning engineer with a background in Mathematics and a home at GitHub Next, GitHub's innovation engine. His main interests are combinations of deductive and intuitive reasoning to improve the software development experience. He's previously worked on developer productivity, ML guided CodeQL, and he was part of the trio that conceived and then implemented the GitHub Copilot project.
Recent project: [https://githubnext.com/projects/copilot-radar/](https://githubnext.com/projects/copilot-radar/)

--

Attend [in person](https://www.kth.se/places/room/id/c9ec01ab-b536-4be6-b82a-0d52ddadb2e6), or online at https://kth-se.zoom.us/j/66538884335

Martin Monperrus

Deepika Tiwari

KTH Software Research Meetup

Technology

Science

Open Source

New Technology

Software Development

Computer Science

Academics

Scholarly Research Outside Academia

Computer Programming

Crafting Code Suggestions using Large Language Models

Room 522, Fantum

Share

KTH Software Research Meetup

Crafting Code Suggestions using Large Language Models

KTH Software Research Meetup

Details

Members are also interested in