Live data from Hacker News

Viewing profile — msvana

msvana

HN member
Joined
Mon, Aug 21, 2023, 11:34 AM UTC
HN karma
49
Public activity
32 items

About msvana

AI and software engineer. Interested in far too many things, including but not limited to AI, software development, economics, philosophy, or psychology.

https://svana.name

Recent public activity

  1. comment
    Comment #47290171

    I think there is one problem with defining acceptance criteria first: sometimes you don't know ahead of time what those criteria are. You need to poke around first to figure out wh…

  2. comment
    Comment #47271954

    I work as an ML engineer/researcher. When I implement a change in an experiment it usually takes at least an hour to get the results. I can use this time to implement a different e…

  3. story
  4. story
  5. story
  6. story
  7. story
  8. story
    Show HN: Read-only AI coding assistant

    I am a bit conservative when it comes to using AI to write code for me. However, I want to use AI to chat about my code - something like ChatGPT that sees my local files. So I star…

  9. story
  10. story
  11. story
    Ask HN: How do you imagine an AI-driven utopia?

    Imagine that the development of artificial superintelligence goes extremely well and we solve any possible obstacle. How do you imagine the ideal future, say in 50 to 100 years?

  12. comment
    Comment #44497129

    This reminds me of the idea that LLMs are simulators. Given the current state (the prompt + the previously generated text), they generate the next state (the next token) using rule…

  13. story
  14. comment
    Comment #44310634

    I had this exact analogy in mind when writing point no. 3

  15. comment
    Comment #44310572

    Thanks, sounds kinda similar to my first point.

  16. story
    Ask HN: Why study anything if AGI is (supposedly) coming?

    I had this question in my head for a few days. So far, I've been able to come up with 4 reasons: 1. It’s about optimizing the worst case. Maybe AGI isn’t coming that soon; we don’t…

  17. story
  18. comment
    Comment #44012476

    Problem no. 2 (Understanding user intent) is relevant not only to writing SQL but also to software development in general. Follow-up questions are something I had in mind for a lon…

  19. story
  20. story
  21. comment
    Comment #43873266

    At the beginning, the article mentions correlation with language skills AND problem-solving. Focusing only on language skills in the second half is misleading. According to the abs…

  22. comment
    Comment #43351882

    Hmm this gave me an interesting project idea: a coding assitant that talks shit about your lack of skills and low code quality.

  23. comment
    Comment #43351719

    Hopefully you'll forgive my ignorance, but this is the first time I hear about DuckDB. What space does it occupy in the DBMS landscape? What are its use cases? How does it compare …

  24. comment
    Comment #43330737

    I have a few thoughts after reading this: - I started to see LLMs as a kind of search engines. I cannot say they are better than traditional search engines. On one hand, they are b…

  25. story