HN Explorer

rs545837

↗ HN profile [ 68.6 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. 1 points 0
  2. 1 points 0
  3. 1 points 0
  4. 1 points 0
  5. 1 points 0
  6. 1 points 0
  7. 1 points 0
  8. 1 points 0
  9. 1 points 0
  10. Structural and semantic component for improving code reviews with local models

    I was curious in improving code reviews because they still suck, so researching on a triage layer that you can attach to your local LLMs/api calls for better code reviews. Most review tools dump a PR diff into a model…

    2 points 0
  11. 1 points 0
  12. 1 points 0
  13. 1 points 0
  14. 1 points 0
  15. What if CRDTs for version control worked at entity granularity instead of lines?
    1 points 0
  16. 1 points 0
  17. 1 points 0
  18. Inspect – Semantic code review. Entity graphs + LLMs (inspect.ataraxy-labs.com)
    1 points 0
  19. 1 points 0
  20. 1 points 0
  21. 1 points 0
  22. 1 points 0
  23. Sem – Semantic Diff behind the new viral merge algo Weave (github.com)
    10 points 1
  24. Weave – A language aware merge algorithm based on entities (github.com)
    188 points 25
  25. Ask HN: Self Sustaining Codebases

    I've been thinking about where codebases are heading as agents write more of the code. Right now the pipeline is: agent writes code, opens a PR, another agent or human reviews it, CI runs all 4000 tests, someone clicks…

    4 points 2