Don't use cosine similarity carelessly(p.migdal.pl)
396 points by stared | 76 comments
Blog post by Piotr Migdał arguing that cosine similarity on embeddings should be used with care and discussing its pitfalls and alternatives.
396 points by stared | 76 comments
Blog post by Piotr Migdał arguing that cosine similarity on embeddings should be used with care and discussing its pitfalls and alternatives.
465 points by fortenforge | 300 comments
Codeium blog post arguing that GitHub Copilot reproduces GPL-licensed code while Codeium excludes non-permissive code from its training data.