Show HN: CLI tool for detecting non-exact code duplication with embedding models

Re:Show HN: CLI tool for detecting non-exact code duplicatio... by rohanat on Thursday July 02, 2026 @02:06PM (#48765233)

have you considered a deterministic tier before the embedding pass? I feel that approach can be more efficient.

[ Parent | on HN ]

Re:Show HN: CLI tool for detecting non-exact code duplicatio... by rkochanowski on Thursday July 02, 2026 @02:26PM (#48765496)

There are good mature tools for deterministic duplication detection and I intentionally focused on embedding-based to fill this gap (I didn't find other tools using this approach).

If by "more efficient" you mean to avoid embedding of the same code multiple times, this optimization is already implemented internally.

[ Parent | on HN ]

Re:Show HN: CLI tool for detecting non-exact code duplicatio... by vander_elst on Thursday July 02, 2026 @02:42PM (#48765675)

We did this by using the ASTs you can go quite far without embeddings and the result is easier to debug and follow what's going on.

[ Parent | on HN ]