Live data from Hacker News

Viewing profile — fendy3002

fendy3002

HN member
Joined
Mon, Aug 13, 2018, 2:54 AM UTC
HN karma
1,152
Public activity
789 items

About fendy3002

No profile information was provided.

Recent public activity

  1. comment
    Comment #49251237

    opus 5 are so bad on this. It often explain it too verbose, and include other things that isn't in the focus but related. ADHD mode helps me greatly on this, though there are some …

  2. comment
    Comment #49120811

    I believe that spam, lies, fraud are negative enforced points during model training, hence when you ask them those, the result will be no / against that. You need to repackage the …

  3. comment
    Comment #49019662

    Oh true, the smaller the org is the better the benefit Still this is a good CYA move from both you and your supervisor, since any concerns are already officially registered, action…

  4. comment
    Comment #49008195

    I understand that people who like to stay on their job dislikes this kind of questions, and I also sympathize on why tech sector now doesn't have places for them and asking people …

  5. comment
    Comment #48965366

    Use untracked file as memory and instruct agent to put progress into that, it'll help managing context in current and new sessions

  6. comment
    Comment #48965322

    > Food advertising has used fake images forever, but it's okay because you know the meatballs don't look like that. Highly disagree. Color retouch or ambience or effects, sure. But…

  7. comment
    Comment #48957738

    Yes, sometimes it's difficult to find the correct driver for Linux and set it up. Having steam machine be start and play like steam deck really brings the console feel on PC. Moreo…

  8. comment
    Comment #48940388

    Your statement reminds me of Avenger's scene where Tony choosing Friday among other AI's catridges to use. That sounds good and practical to happen!

  9. comment
    Comment #48744709

    oh but it'll be very2 helpful and the time spent will be short. It's easy to verify: * new contributor? * more than 10 files affected (higher count are more valid)? * wall of text …

  10. comment
    Comment #48560875

    Curiosity or anticipation I think. I have tried it in the name of those 2 factors, because when the frontier model price increase happens and we don't know anything about local mod…

  11. comment
    Comment #48482684

    Thankfully Microsoft doesn't let it's windows or xbox team do the naming of their latest ai model, otherwise MAI flash 360 series X will take the cake

  12. comment
    Comment #48475885

    Opus will be gutted furthermore. /s I feel 4.8 is very slow in last 2 days

  13. comment
    Comment #48475750

    20x the cost means you need to have fable to be 20x better than the alternative, which is a tall order. And there's more options out there too, perhaps the 4x cost is enough. This …

  14. comment
    Comment #48333122

    If they (AI) able to compete with even 30% of workforce, that alone is a big enough leverage over the already powerful companies. At minimum it will cause another phase of wealth i…

  15. comment
    Comment #48318456

    tried it myself, not much of difference https://gist.github.com/fendy3002/3026a8c4d67d1301666ec40fc0... looks like the model already trained well on both bicycle and pelicans

  16. comment
    Comment #48306679

    IJKL for movement instead WASD? An interesting approach...

  17. comment
    Comment #48304997

    benefits for the commoner? not in a million years they will support that

  18. comment
    Comment #48303534

    it's so frustrating in Cities Skylines without mods, that it's so common difference in height causing so much placement issues

  19. comment
    Comment #48248145

    Never used 4.7 outside CC extension VSCode. TIL, will keep that in mind

  20. comment
    Comment #48246373

    4.7 is better if your spec is clearer. 4.6 is better if you give it more freedom doing it's tasks. 4.6 felt it'll steer off often if you give detailed specs than 4.7 though, so per…

  21. comment
    Comment #48246164

    As always, I think this happen more to vibe coder. They don't understand that bigger project means worse AI performance. On top of that Opus felt being nerfed at understanding prom…

  22. comment
    Comment #48246152

    Oh Opus is nerfed sure, but not that hard. Early this year opus 4.6 can understand your prompt and your intention easily, it got worse around mid April. Opus 4.7 even worse than th…

  23. comment
    Comment #48246118

    For me I need to compare the code generated before committing. Also I need to read markdown plans generated for review before commit to execution. VSCode CC extension also generate…

  24. comment
    Comment #48246091

    Stay with 4.6 if you can, it is disabled (afaik) on vscode claude code extension. 4.7 IMO is around 10-20% worse at understanding your prompt intention. You need more effort to exp…

  25. comment
    Comment #48236895

    if constructing houses or buildings are quick, the bottleneck will be moved to other things. Like city planner, regulations / legals, material procurements, furnishing / equiments,…