Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep

Re:Show HN: Semble – Code search for agents that uses 98% fe... by shermantanktop on Monday May 18, 2026 @03:49AM (#48176621)

Do inefficient grep/sed behaviors have a secondary benefit in seeding the context with breadcrumbs of code from irrelevant matches?

[ Parent | on HN ]

Re:Show HN: Semble – Code search for agents that uses 98% fe... by Bibabomas on Monday May 18, 2026 @05:26AM (#48177204)

In theory maybe, but in practice it hurts more than it helps I think. Irrelevant context makes the model more likely to reason from the wrong code (and it's slower and more expensive).

[ Parent | on HN ]