Chunking 2M files a day for code search using syntax trees

Re:Chunking 2M files a day for code search using syntax trees by kevinlu1248 on Monday July 31, 2023 @05:48PM (#36949332)

That's interesting, I've seen a few papers about this. I'm personally curious about editing syntax trees using language models, since it would prevent syntax errors altogether.

[ Parent | on HN ]

Re:Chunking 2M files a day for code search using syntax trees by vladf on Tuesday August 01, 2023 @12:31AM (#36952319)

Which papers?

[ Parent | on HN ]

Re:Chunking 2M files a day for code search using syntax trees by kevinlu1248 on Tuesday August 01, 2023 @12:57AM (#36952494)

Here's some of the papers: https://arxiv.org/abs/1911.09983 and https://aclanthology.org/2021.findings-acl.384.pdf

[ Parent | on HN ]

Re:Chunking 2M files a day for code search using syntax trees by madeofpalk on Tuesday August 01, 2023 @06:07AM (#36954277)

In my limited use, I've never seen these models (chatgpt, and github copilot) generate invalid syntax. I don't see much to improve there

I do see them generate code that fails the type checker though.

[ Parent | on HN ]

Re:Chunking 2M files a day for code search using syntax trees by kevinlu1248 on Tuesday August 01, 2023 @04:20PM (#36962159)

For editing code there's a decent chance of syntax errors or undefined variables since it's only modifying a subset of the code.

[ Parent | on HN ]