Live data from Hacker News

Viewing profile — ting0

ting0

HN member
Joined
Thu, Feb 26, 2026, 4:10 PM UTC
HN karma
39
Public activity
58 items

About ting0

No profile information was provided.

Recent public activity

  1. comment
    Comment #48120773

    Do you think Prometheus + Grafana is the way to go?

  2. comment
    Comment #48119590

    This looks cool

  3. comment
    Comment #47900733

    It's not clear to me how or why this works, and how it compares to just using md files in my project. For something like this, we really need benchmarks.

  4. comment
    Comment #47900681

    Hey man, if it works it works. There's a reason everyone is creating AI tools. We're all buying them. I'm still waiting for someone to make a world-class cli harness that can repla…

  5. comment
    Comment #47898601

    It's terrible, don't waste your time like I did. That bench means nothing by the way.

  6. comment
    Comment #47895786

    > It’s my experience that models that perform very well on benchmarks do not necessarily perform well in real life Well, yeah... Like Opus 4.5, 4.6, 4.7. Top of the benchmarks and …

  7. comment
    Comment #47895762

    This is nonsense. The real reason is because the US companies are scamming the public, as per usual.

  8. comment
    Comment #47895754

    They don't make sense, they're a lie that these AI companies keep spamming using bots so that useful idiots perpetuate it, so that they can keep draining us of money. Straight out …

  9. comment
    Comment #47834931

    Well this sucks. It's funny that Blizzard with its vast empire of wealth can't even compete with TurtleWoW.

  10. comment
    Comment #47834887

    Don't waste your time. I've been down this road and unless you've got business connections or a LOT of marketing money, it is not worth attempting.

  11. comment
    Comment #47814378

    No, but the AI labs would love to frame it this way so they can continue to nerf models and increase prices while they use the cheap, highly performant, highly powerful models inte…

  12. comment
    Comment #47762555

    The Twitter example is a bad one. Elon Musk, at the time, was making hundreds-of-millions through crypto-market manipulation on Twitter. At that time he realized that having contro…

  13. comment
    Comment #47672519

    Has anyone ever done a proper security audit of VLC that is downloaded from the web? I don't trust it, and the fact that their releases on Github don't include binaries makes me tr…

  14. comment
    Comment #47664872

    Thinking time is not the issue. The issue is that Claude does not actually complete tasks. I don't care if it takes longer to think, what I care about is getting partial implementa…

  15. comment
    Comment #47664799

    Do you guys realize that everyone is switching to Codex because Claude Code is practically unusable now, even on a Max subscription? You ask it to do tasks, and it does 1/10th of t…

  16. comment
    Comment #47644812

    Whenever Anthropic has an opportunity to do what's right, they go the opposite way. For example, their source leaks, and instead of open-sourcing it like people have been asking to…

  17. comment
    Comment #47570531

    They're just removing it from public access and selling it to big money instead. Think large advertising companies, government agencies, Coke-Cola, Hollywood, etc. The scary part i…

  18. comment
    Comment #47570490

    The only reason to ever use LinkedIn is if you're in the process of finding a job. Other than that, it's a cesspit. Even for that though, I've never used it, and I don't feel like …

  19. comment
    Comment #47540182

    You have a problem with generating synthetic data from test questions? Humans simulate experiences in their mind. What's the problem?

  20. comment
    Comment #47540172

    Does it matter though? If it accomplishes the task, it accomplishes the task. Everyone uses a harness anyway, and finding the best harness is relevant. Also perhaps this hints at s…

  21. comment
    Comment #47533000

    They will certainly get worse. LLMs make it so much easier.

  22. comment
    Comment #47532971

    I feel like they should be legally responsible for providing scanning infrastructure for this sort of thing. The potential economic damage can be catastrophic. I don't think this i…

  23. comment
    Comment #47513563

    And raise the pay.

  24. comment
    Comment #47508231

    How does this compare to raw https://github.com/vercel-labs/agent-browser ?

  25. comment
    Comment #47508178

    There's no mystery here. His son Oil Barron Trump has been doing the same thing, along with Trump, in the crypto markets and online prediction markets for years now. They've made o…