Discussion on "I Let My LLM Guess a Number My Own Code Already Knew"

Ashish Babu · 2026-07-25T03:30:00.000Z

When I built the matching engine for ProximaHire — a semantic job-matching tool that compares resumes to job listings using vector embeddings — the core idea was simple: compute a cosine similarity sc

The 768-versus-384 dimension guard is useful, but model identity needs to be first-class metadata too. Two embedding models can produce vectors with the same dimension and still occupy incompatible spaces, so a dimension check alone can silently pass bad comparisons. I would store model name, revision, and normalization settings with every row, then partition or migrate the index whenever that fingerprint changes.

Good catch, and honestly you're right that I only check dimension right now, not model identity. Didn't think about the case where two different models spit out the same dim but totally different vector spaces — that's a real hole, not just a theoretical one since I'm already juggling Ollama locally vs HuggingFace in prod.

Storing model name + revision alongside each row makes sense. Only thing I'd add on my end is I'd probably also need a one-time re-embed job for anything already in the table before I flip a hard check on, otherwise I lock myself out of my own data.

Appreciate you actually reading closely enough to catch this, going to go fix it.

Fixed this, added model identity tracking, guards against both mismatched and missing model IDs now, existing embeddings force a re-embed instead of guessing.

Here's the commit: github.com/ashish-babu-03/ProximaHire/commit/31b1…

Appreciate you catching it :)

Nice fix. For the one-time re-embed I would avoid rewriting the live index in place: write a new namespace keyed by the new fingerprint, validate row coverage plus a small retrieval regression set, then atomically swap the alias. That gives you a rollback path if normalization or the model revision behaves differently and keeps mixed spaces impossible during migration. Missing model IDs can remain quarantined as legacy data until that migration completes rather than being inferred from dimension.

Search Hashnode

I Let My LLM Guess a Number My Own Code Already Knew

Responses(4)