Live data from Hacker News

Viewing profile — krystofee

krystofee

HN member
Joined
Mon, May 31, 2021, 12:24 PM UTC
HN karma
57
Public activity
51 items

About krystofee

meet.hn/city/cz-Capital-City-of-Prague

Socials:

- linkedin.com/in/krystofee - github.com/krystofee

Interests:

Climbing, Cycling, Hiking, Music, Outdoor Activities, Programming, Startups, UI/UX Design, Web Development

---

Head of development @ retino.com

Recent public activity

  1. story
  2. comment
    Comment #48752578

    its bloated, try /radio

  3. comment
    Comment #47667332

    Pi.dev is an open-source CLI coding agent by @badlogic. It lets you steer the agent while it works, but steering puts future tasks into the context — and LLMs rush through early ta…

  4. story
  5. comment
    Comment #47192597

    How come this is signed by OpenAI engineers while OpenAI participates in it with DoW? https://x.com/sama/status/2027578652477821175

  6. comment
    Comment #47052692

    Does anyone know when will possibly arrive 1M context windows to at least MAX x20 subscriptions for claude code? I would even pay x50 if it allowed that. API usage is too expensive…

  7. comment
    Comment #47036490

    Funny that this age was probably written by AI hence the "how to write modern css" is completely irelevant.

  8. comment
  9. story
  10. comment
    Comment #46614405

    I disagree with the "confidence trick" framing completely. My belief in this tech isn't based on marketing hype or someone telling me it's good – it's based on cold reality of what…

  11. comment
  12. story
  13. comment
    Comment #45876334

    Is there any easy way to implement this pattern in AWS RDS deployments where we need to deploy multiple times a day and need it to be done in few minutes?

  14. comment
    Comment #45864564

    Their docs show throughput limits (e.g., 4 CPU = 60 errors/sec), but what happens during error spikes? If my app crashes and blasts hundreds of errors in seconds, does Telebugs hav…

  15. comment
    Comment #45792083

    Isnt it huge deal, that this 30B model can compare and surpass huge closed models?

  16. comment
    Comment #45471012

    try /context in Claude Code

  17. comment
    Comment #45231561

    I’m experiencing something similar. We have a codebase of about 150k lines of backend code. On one hand, I feel significantly more productive - perhaps 400% more efficient when it …

  18. comment
    Comment #45115640

    I think its a matter of time when we will have photorealistic playable computer games generated by these engines.

  19. story
  20. comment
    Comment #44291878

    Is there some clean way to pass components or just html to components using this framework without having them in strings? This is issue I see with most of these approaches.

  21. comment
    Comment #43773017

    Sadly this article just compares pricing. When we were using Google instead of HERE, results were mostly better but not worth the price. I would rather see some opinions on the qua…

  22. comment
    Comment #43722088

    This is just because TS doesnt have keyword or keyword-only arguments as Python for example has.

  23. comment
    Comment #43459620

    when you present this to LLM, it will be confused the same as a human reading this

  24. comment
    Comment #43459609

    Think about it, what do you read when integrating APIs, code or documentation?

  25. comment
    Comment #43375403

    My take is: its either there with all of its features and popularity or its not. The argument that it will be taken down if its more popular seems to me fundamenally wrong.