HN Explorer

bonigv

↗ HN profile [ 82.1 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. 1 points 1
  2. Show HN: Is grep enough? A transparent benchmark for agentic code navigation (entelligentsia.github.io)

    Felt LSP Servers were too complex. Bash tools alone too brutish. Wanted to see what if it is a tree-sitter as a firstclass tool. Ran a bench over 10 large codebases [bitcoin, django, rails, redis,...] at 5 levels of…

    3 points 3
  3. Ask HN: How do we measure software in LLM era?

    A bit of a rant. Sorry! With the probablistic pluggable 'brain' existing in parts of the solution how are you measuring anything is better or worse? I am at a loss to quantify whether anything is improving or worsening…

    1 points 6
  4. Ask HN: What do you do to save tokens?

    Lots of products working on saving-tokens-space. Compression, Tool Output rewrite, Sitting as proxy Cache between harness and provider , doing circus with interceptor hooks - these are some of the approaches we are…

    4 points 2
  5. Show HN: Grove – fast source insights for coding agents – via Tree-sitter (github.com)
    4 points 1
  6. Ask HN: Will we start seeing tools for LLM use?

    Many projects and addons exists to reduce the verbosity on standard bash / git /npm etc. Commands that agents pass regularly as tools to LLMs. (eg. rtk, headroom, lean-ctx). Tool output compression does yield good token…

    3 points 2
  7. 1 points 0
  8. How to tell stories with Streetview (producthunt.com)
    1 points 0