An NSFW filter for Marginalia search
speckx
94 points
16 comments
March 30, 2026
Related Discussions
Found 5 related stories in 30.5ms across 3,471 title embeddings via pgvector HNSW
- Show HN: Veil – Dark mode PDFs without destroying images, runs in the browser simoneamico · 66 pts · March 26, 2026 · 42% similar
- A tool that removes censorship from open-weight LLMs mvdwoord · 144 pts · March 06, 2026 · 39% similar
- Show HN: Modembin – A pastebin that encodes your text into real FSK modem audio a13x57 · 12 pts · March 03, 2026 · 38% similar
- Show HN: Modembin – A pastebin that encodes your text into real FSK modem audio a13x57 · 24 pts · March 06, 2026 · 38% similar
- Show HN: uBlock filter list to blur all Instagram Reels shraiwi · 109 pts · March 02, 2026 · 38% similar
Discussion Highlights (4 comments)
marginalia_nu
This was a very meandering project, and trying to corral it into some sort of coherent narrative was a bit of an undertaking on its own. Hopefully it makes some sense.
8organicbits
Have you seen many examples of websites labeling themselves, perhaps using rating meta tags (<meta name="rating" ...>)? Self-labeling seems valuable in some ways, but I don't think I've seen it catch on.
ChadNauseam
Does marginalia_nu not use embedding models as part of search? I guess I assumed it would. If you have embeddings anyway, decision trees on the embedding vector (e.g. catboost) tend to work pretty well. Fine-tuning modernbert works even better but probably won't meet the criteria of "really fast and run well on CPUs". That said, the approach described in the article seems to work well enough and obviously provides extremely cheap inference
VorpalWay
Looks like a cool search engine! Hadn't heard about it before. But the search page says "Simple technology, no AI". With this change, that is no longer true though, is it? Of course the definition of "AI" is extremely vague. Once upon a time, A-star search was considered AI after all.