HN Explorer

DanyWin

↗ HN profile [ 132 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. 1 points 0
  2. 1 points 0
  3. Show HN: Duck Talk – Real-time voice interface to talk to your Claude Code (github.com)
    6 points 0
  4. Vibe coding as a VC (kevinkuipers.substack.com)
    24 points 12
  5. 1 points 0
  6. 1 points 0
  7. 1 points 0
  8. Local Embeddings and LLMs Can Outperform OpenAI and Gemini for Web Navigation (blog.lavague.ai)
    2 points 0
  9. LaVague: Open-source Large Action Model to automate Selenium browsing (github.com)
    378 points 97
  10. Show HN: LaVague – Automatic Selenium code generation from natural language (github.com)
    1 points 0
  11. LaVague: Text2Action AI pipeline to turn natural language into browser actions (github.com)
    3 points 0
  12. 'sleeper agent' AI assistants can sabotage your code without you realizing (theregister.com)
    2 points 1
  13. 1 points 0
  14. 1 points 0
  15. 1 points 0
  16. 1 points 0
  17. 1 points 0
  18. Best framework to create synthetic data for finetuning small models?

    Hi everyone, With the different data points, such as phi-1.5 performance being as good as 7b models on some tasks, it seems to be plausible that small models can be quite capable on specific tasks. I am working on…

    1 points 0
  19. 1 points 0
  20. 1 points 0
  21. Show HN: OSS, private and in-browser Conversational AI with local model (github.com)
    2 points 0
  22. 1 points 0
  23. 1 points 0
  24. Zero-trust AI APIs serving Llama 2 70B inside enclaves (blindllama.mithrilsecurity.io)
    35 points 9
  25. BlindLlama: Open-source Zero-trust AI APIs for transparent and private AI (github.com)
    2 points 0