# Cosine Similarity vs Claude: What Happens When They Disagree

DevFeed: [Cosine Similarity vs Claude: What Happens When They Disagree](<https://devfeed.tech/articles/cosine-similarity-vs-claude-what-happens-when-they-disagree-40129.md>)

Original publisher: [Read original article](<https://korbonits.com/blog/2026-04-05-two-scores-one-pair-of-sentences/>)

Published: 2026-04-05T00:00:00Z

Content type: comparison

Language: en

Sources: [Alex Korbonits](<https://devfeed.tech/sources/alex-korbonits.md>)

Topics: [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [AI search](<https://devfeed.tech/topics/ai-search.md>)

Tags: [claude](<https://devfeed.tech/tags/claude.md>), [embedding](<https://devfeed.tech/tags/embedding.md>), [search](<https://devfeed.tech/tags/search.md>), [semantic](<https://devfeed.tech/tags/semantic.md>)

## AI overview

This article compares cosine similarity from embedding models with Claude's assessment of sentence meaning. Using "I love you" and "I hate you" as an example, it explains why embeddings can place antonyms close together and describes the distributional basis of modern sentence embeddings.

## Source excerpt

I built semantic search for my blog and a dual-score similarity tool. The cases where a real embedding model and Claude disagree are more interesting than the cases where they agree.