Live data from Hacker News

Viewing profile — sudoapps

sudoapps

HN member
Joined
Wed, Jan 08, 2020, 3:10 AM UTC
HN karma
79
Public activity
46 items

About sudoapps

No profile information was provided.

Recent public activity

  1. story
  2. story
  3. comment
    Comment #47746859

    Awesome! Let me know if you run into any issues with the setup.

  4. comment
    Comment #47746497

    Coding agents have changed how I build. Constantly switching between the terminal and an IDE started to feel inefficient, so I wanted a better terminal-first setup where I could ma…

  5. comment
    Comment #47720510

    Coding agents should help us reduce dependencies overall. I agree Go is already best positioned as a language for this. Using random dependencies for some small feature seems archa…

  6. story
  7. story
  8. story
  9. story
  10. story
  11. comment
    Comment #47239793

    Hot take - Local LLM computing will move to stationary, always on devices (Mac mini & studio). Developers and users will move to lighter, portable devices to interface with their l…

  12. comment
    Comment #47219777

    Codex built my old startup in a weekend. What took me a few months to build 2+ years ago can now be done with coding agents in 2 days. The last couple months feel like a step chang…

  13. story
  14. story
    Show HN: Night Watch, zero-dependency DevOps agent

    Night Watch is a zero-dependency DevOps agent. It uses an LLM agent to run diagnostics, inspect cloud/log signals, and correlate issues with code changes.

  15. story
  16. story
  17. story
  18. comment
    Comment #38745774

    How do others feel about the pace of innovation in AI? Is there ever a reason to slow down advancements in a given field?

  19. story
  20. comment
  21. comment
    Comment #36434226

    Speed and performance improvements like this are why VSCode has passed Atom and other editors over time.

  22. story
  23. story
  24. comment
    Comment #36154146

    Very similar to a consensus network. That is probably the future of LLM agents.

  25. comment
    Comment #36127526

    This was a quick experiment on creating multiple LLM (GPT) agents with their own objective to see if outputs can be improved.