HN Explorer

msvana

↗ HN profile [ 56.4 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. I built an RGB controller with Arduino (svana.name)
    9 points 1
  2. Do LLMs hallucinate more in Czech than in English? (svana.name)
    2 points 0
  3. Hallucinations in LLMs: What are they and what causes them (svana.name)
    1 points 1
  4. Managing GPU Rentals with Rsync: Workflow for Volatile Cloud Resources (svana.name)
    2 points 0
  5. Implementing a local AI coding agent is hard (svana.name)
    2 points 1
  6. Show HN: Read-only AI coding assistant (github.com)

    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 started working on FileChat. FileChat is…

    1 points 0
  7. How I solved PyTorch's cross-platform nightmare (svana.name)
    73 points 12
  8. Lessons from AI Safety for Businesses (svana.name)
    1 points 0
  9. 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?

    1 points 2
  10. LLMs Are Simulators (alignmentforum.org)
    1 points 0
  11. 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 know. So it might be worth being…

    5 points 11
  12. The value of commercial coding courses (svana.name)
    1 points 0
  13. Would I do a PhD again? (svana.name)
    2 points 0
  14. AI-LieDar: Examine the Trade-Off Between Utility and Truthfulness in LLM Agents (arxiv.org)
    1 points 0
  15. Progress in AI requires thinking beyond LLMs (infoworld.com)
    1 points 1