from Hacker News

Will LLMs Eclipse the Classic Code Diff Algorithms?

by baristaGeek on 11/9/23, 8:15 PM with 4 comments

• by DarkPlayer on 11/9/23, 8:45 PM

  I think LLMs will have a hard time replacing traditional diff algorithms. You want your diff to be reliable and predictable. It shouldn't omit relevant changes. This is not really a strength of LLMs.

  I think a system that parses the code and uses verifiable rules to hide invariant changes would have a much easier time being adopted. I may be biased since I work on SemanticDiff (think difftastic but for VS Code and GitHub) and have implemented such rules myself. There have been several times where I've thought about implementing a new rule, only to find out that some obscure edge case would not be handled correctly. So I don't see how LLMs could handle these cases correctly in the near future.

• by al2o3cr on 11/9/23, 8:31 PM

  Github (and I'm sure plenty of other tools) already do this with deterministic code.

  Why on Earth would you want to replace that with an LLM that might hallucinate?