Live data from Hacker News

Viewing profile — RayVR

RayVR

HN member
Joined
Sun, May 29, 2011, 1:57 AM UTC
HN karma
1,349
Public activity
260 items

About RayVR

No profile information was provided.

Recent public activity

  1. comment
    Comment #49053499

    My own experience is that with the best models, if you provide reasonable tools, with progressive discovery, and a semi-clear user request, the system prompt is essentially worthle…

  2. comment
    Comment #48963991

    Yes, this is already accounted for in many benchmarks, but without deep context of the problem type, the top line pricing is the best starting point. In my own experience, Fable is…

  3. comment
    Comment #48877396

    Non-competes in finance almost always come with compensation during the defined period. The idea that a company can restrict at-will employee’s post-separation employment is absurd…

  4. comment
    Comment #48469184

    I gave fable 5 a task for which opus has been really really underperforming. Fable 5 took far less time and produced actually useful analysis. Instead of just regurgitating roughly…

  5. comment
    Comment #48318088

    I have been using opus 4.8 all morning and this is honestly the most sycophantic, ChatGPT like experience I have had from Anthropic. Very concerning.

  6. comment
    Comment #48141663

    My own experience has been that it works for about five minutes before it just disconnects or hangs. I’ve never been able to use it successfully.

  7. comment
    Comment #47888583

    My first experience with 5.5 via ChatGPT was immensely disappointing. It was a massive reduction in quality compared to 5.4, which already had issues.

  8. comment
    Comment #47814542

    As with anything, it depends on the quality and skills of the people doing the designing. I have yet to really work with a designer that embedded themselves enough in the UX to des…

  9. comment
    Comment #47525838

    Who cares? I used Claude code to build a custom notes application for my specific requirements. It’s not perfect, but I barely invested 10 hours in it and it does almost everything…

  10. comment
    Comment #47358830

    These bear related sayings always make me laugh. The one I was told by a Russian: “don’t argue over how to skin the bear before you’ve killed it”

  11. comment
    Comment #47330714

    That’s hilarious

  12. comment
    Comment #47241611

    This is powerful. You’re finally saying the quiet part out loud. /s

  13. comment
    Comment #47241580

    Did you read the article? Author is talking about humans relying on chatbots to formulate all their responses for them without strict direction and refinement.

  14. comment
    Comment #46870319

    I'm sorry, but the music on the demo video is the most atrocious nonsense. I know it's crazy, but it makes me hate the app. openAI is falling off hard.

  15. comment
    Comment #46729532

    I have often found proton’s intrusive marketing campaigns annoying. I use them for email and that’s all I want. Every time they market some new product to me, I get closer to movin…

  16. comment
    Comment #46685452

    Every time I open threads it’s mostly ChatGPT garbage from wannabe tech or finance influencers.

  17. comment
    Comment #46582071

    I think the key thing here is in point 2. I’ve wanted a good markdown editor with automatic synchronization. I used to used inkdrop. Which I stopped using when the developer/owner …

  18. comment
    Comment #46560986

    Why should anthropic open source Claude Code CLI? I understand you and some others want it, maybe it would be better for the community, but is it what’s best for anthropic? Why sho…

  19. comment
    Comment #46270259

    I saw that rootmy.tv works for some versions of webos.

  20. comment
    Comment #46190176

    I'm not arguing that human brains are magic. the current AI models will probably teach us more about what we didn't know about intelligence than anything else.

  21. comment
    Comment #46188160

    Are you a stream of words or are your words the “simplistic” projection of your abstract thoughts? I don’t at all discount the importance of language in so many things, but the que…

  22. comment
    Comment #45736574

    I feel terrible for anyone relying on anything you produce as a proompt engineer

  23. comment
    Comment #45650418

    This author obviously has no experience with investment banks. OpenAI is massive, fairly risky, associated with Microsoft, etc. all true. What matters to JPM is potential future bu…

  24. comment
  25. comment
    Comment #45617091

    Interesting. Not my experience at all. It makes mistakes that GPT-4 used to make: mixing languages (using Python syntax in C++ when I never asked any Python questions), imagining A…