Live data from Hacker News

Viewing profile — Philip-J-Fry

Philip-J-Fry

HN member
Joined
Wed, Jul 15, 2020, 6:56 PM UTC
HN karma
3,714
Public activity
557 items

About Philip-J-Fry

No profile information was provided.

Recent public activity

  1. comment
    Comment #49216452

    The top nav is completely broken for me.

  2. comment
    Comment #49207815

    Cerebras doesn't etch the model onto silicon though. They're basically just wafer scale GPUs. They're more flexible than etched silicon though because they can just run the next ve…

  3. comment
    Comment #49153529

    "Do your own research" is definitely a defensible position. No one is saying take Claude's output as fact. These people would still ask and waste your time without AI. The fact is,…

  4. comment
    Comment #49152342

    Literally just ignore these people if they don't get the message. Let them complain to their supervisor and hopefully their supervisor will bring up the fact that you asked them to…

  5. comment
    Comment #49152196

    "Hey, here's what I found. By the way I used Claude to get this info. It might be worth trying that yourself if you have similar questions, it's quite good at this in my experience…

  6. comment
    Comment #49133448

    I've seen two camps of people within the same company I work at. Some think AI is generating acceptable code. Others think it's generating slop. I sit in the middle a lot of the ti…

  7. comment
    Comment #49133309

    When you're in the trenches actually making code changes yourself, you get irritated and are driven towards improving the code as you implement new features. AI never does because …

  8. comment
    Comment #49133137

    I think they're saying that the people who aren't software developers are playing around with Claude Code. And that's not what their job is and it's not what they understand. It's …

  9. comment
    Comment #49133118

    I think of it this way. If AI could build the product alone, then why would it ever be worth more than the tokens you spent on it? I think this would hold true 99% of the time. It'…

  10. comment
    Comment #49114901

    In my real world use Luna is as useful to me as Sonnet. And it gets stuff done faster and follows my instructions more closely.

  11. comment
    Comment #49035709

    The port was line for line and full of unsafe code. It didn't prevent any bugs. They're not using Rust for its strengths.

  12. comment
    Comment #48985305

    A website shouldn't be pinning CPU or GPU. When people run a game they expect some sort of battery drain. People don't expect that some websites will thrash your CPU/GPU like a gam…

  13. comment
    Comment #48976362

    One LLM prompt can't get you $500K. Why would someone spend $500k instead of just prompting themselves?

  14. comment
    Comment #48975517

    Don't you just throw all the washing into the washing machine, wait for it to actually do the work, and then hang it all up afterwards? It's like a 15 minute job max.

  15. comment
    Comment #48971805

    Who said they're new? Also, you can encounter new segfaults in a codebase just by executing code paths you haven't seen before.

  16. comment
    Comment #48970513

    Segfaults were a thing with the Zig version. Purely based on the fact it's a line by line translation of the Zig code to unsafe Rust, all the Zig code that caused segfaults is goin…

  17. comment
    Comment #48970422

    As far as I can remember the origins of Bedrock are the original console releases which couldn't ship a JVM. So a whole new codebase was developed, and ultimately it was more perfo…

  18. comment
    Comment #48969217

    That's what half of people's AI developed projects feels like to me. I have colleagues using Openclaw, and having an entire team of agents managing their home infrastructure. And I…

  19. comment
    Comment #48941147

    They're just saying that like Suno Music, if you look closely the cracks show. They're not saying the music is AI generated.

  20. comment
    Comment #48828487

    That depends entirely on how you're using AI. If you're getting it to do all the hard thinking, then sure using the best model is probably always going to be better. But it's also …

  21. comment
    Comment #48794901

    I've went on a similar journey and did just end up going to back SQL. Mapping database rows to domain objects really isn't that painful and you only do it once. So not a big deal. …

  22. comment
    Comment #48736423

    Dunno, it seems like the exact kind of thing Claude would think up if you asked it to subtly alter the system prompt to hide this info. It's all a losing battle anyway.

  23. comment
    Comment #48613678

    I commented on the original post and I still don't understand the point of a "Visual Designer" basically reimplementing Windows XP in the browser. What are you trying to show off? …

  24. comment
    Comment #48529443

    I have one too. He'll say "Claude says this:" and pastes a screenshot of some Claude Code output. Most of the time it's wrong, or makes assumptions that won't hold true. Or it come…

  25. comment
    Comment #48529390

    It depends on where you're using AI. If you're working on a project for yourself or in a tiny company. Then sure, writing the code probably was your bottleneck. But at mid to large…