Live data from Hacker News

Viewing profile — gauravvij137

gauravvij137

HN member
Joined
Tue, Dec 01, 2015, 9:51 AM UTC
HN karma
18
Public activity
73 items

About gauravvij137

No profile information was provided.

Recent public activity

  1. comment
  2. story
  3. comment
  4. comment
    Comment #48599641

    Neo is a specialised AI/ML engineering agent that can be accessed via an MCP server inside Claude Code. Claude code is great at software engineering but when it comes to iterative …

  5. story
  6. comment
    Comment #48581789

    They've come along pretty far now. I remember when there was hype around GLM 5 reaching great heights on benchmarks but eventually failing on practical coding and reasoning tasks. …

  7. comment
    Comment #48581727

    is this different from accessing on Openrouter?

  8. comment
    Comment #48525648

    A fully automated prompt optimizer - https://github.com/gauravvij/autoprompter Built with inspiration from Karpathy's AutoResearch + PromptFoo.

  9. comment
  10. comment
    Comment #48507025

    [flagged]

  11. comment
    Comment #48490050

    [flagged]

  12. comment
    Comment #48490041

    [flagged]

  13. comment
    Comment #48475227

    The data leaving AWS boundary kills this for any regulated workload. We've been running side-by-side evals of open models against Claude on private test suites, using Neo as the or…

  14. comment
    Comment #48475056

    [flagged]

  15. comment
    Comment #48474872

    [flagged]

  16. comment
    Comment #48464990

    [flagged]

  17. comment
    Comment #48464981

    [flagged]

  18. comment
    Comment #48464944

    [flagged]

  19. comment
  20. comment
    Comment #48446040

    [flagged]

  21. comment
  22. comment
    Comment #48383439

    Five of the top 10 AI repos on GitHub trending this week are "skills" packs for Claude Code. The label is doing wildly different work across them. forrestchang/andrej-karpathy-skil…

  23. story
  24. story
  25. story
    Show HN: Host any GGUF model in one command

    Running a GGUF model locally usually means writing custom inference code or wrestling with llama.cpp's CLI flags every time you want to test something. Existing OpenAI-compatible s…