Re:Portal by Spotify cut my Claude Code token usage by 90%
by ahmedelsama on Saturday September 05, 2026 @10:34AM
(#49576909)
The Bloom filter framing is right. What made it work for me: the cheap model is only allowed to point, never to decide. Once it stopped judging anything and just returned file paths and line ranges, the quality complaints disappeared. The expensive model still does all the reading that matters, just on 10% of the bytes.
[ Parent
| on HN ]
Re:Portal by Spotify cut my Claude Code token usage by 90%
by lxgr on Saturday September 05, 2026 @11:38AM
(#49577587)
Unlike an actual Bloom filter (which does not return false negatives), the cheaper model is still trusted to correctly recognize synonyms, equivalent functional constructions etc.
One is strictly a performance optimization, the other is a speed/quality tradeoff. It might well be a very good one, but it’s a tradeoff nevertheless. The framing is misleading.
Re:Portal by Spotify cut my Claude Code token usage by 90%
by astrange on Saturday September 05, 2026 @02:37PM
(#49579363)
That's a Claude.