Live data from Hacker News

Viewing profile — rynn

rynn

HN member
Joined
Fri, Feb 16, 2024, 6:42 PM UTC
HN karma
50
Public activity
30 items

About rynn

No profile information was provided.

Recent public activity

  1. comment
    Comment #48929895

    That doesn’t mean they won’t be, or that the forks won’t be good.

  2. comment
    Comment #47764599

    If you woke up and found you couldn't log into to anything that required a code, you're not alone.

  3. story
  4. comment
    Comment #47541862

    API almost there too

  5. comment
    Comment #46938775

    Amazing utility that just works. Windows version of ‘locate’ IIRC it loads the FS index into memory and queries directly off of it. If a simple metadata search is enough for you I …

  6. comment
    Comment #46594892

    9 years into transformers and only a couple years into highly useful LLMs I think the jury is still out. It certainly seems possible that some day we'll have the equivalent of an E…

  7. comment
    Comment #46406512

    Awesome, in that case, I'll check it out!

  8. comment
    Comment #46406497

    >What is keeping Google/Amazon/Microsoft from licensing Groq’s tech? Nothing, but they likely can't implement it as well as they could had they bought Groq first.

  9. comment
    Comment #46401898

    > licensing with BSL when basically every month the AI world is changing is not a smart decision This turned me off as well. Especially with no published pricing and a link to a si…

  10. comment
    Comment #46378175

    Where spies == logging and they tell you, and provide clear opt out instructions

  11. comment
    Comment #46360968

    > I think the DGX Spark will likely underperform the M4 from what I've read. For the DGX benchmarks I found, the Spark was mostly beating the M4. It wasn't cut and dry.

  12. comment
    Comment #46360512

    > Please do give that a try and report back the prefill and decode speed. M4 Max here w/ 128GB RAM. Can confirm this is the bottleneck. https://pastebin.com/2wJvWDEH I weighed abou…

  13. comment
    Comment #46360408

    gpt-5.2 codex isn't available in the API yet. If you want to be picky they could've compared it against gpt-5 pro gpt-5.2 gpt-5.1 gpt-5.1-codex-max gpt-5.2 pro all depending on whe…

  14. comment
    Comment #46349892

    What are you working on that you’ve had such great success with gpt-oss? I didn’t try it long because I got frustrated waiting for it to spit out wrong answers. But I’m open to try…

  15. comment
    Comment #46349882

    It will be like the rest of computing, some things will move to the edge and others stay on the cloud. Best choice will depend on use cases.

  16. comment
    Comment #46340913

    Where did you get all the data? The justice.gov site didn’t have a mass download option that I could find.

  17. comment
    Comment #46259050

    > I recognize this is a hard concept to understand for folks on this site, but the average joe signing up for a VPN doesn't even remotely understand what they are doing and why. Re…

  18. comment
    Comment #46258799

    > Is there any real-life situation in which this matters, though? You’d be shocked at the number of people in regulated industries that thinks a VPN inherently makes them more secu…

  19. comment
    Comment #46258752

    Do you use Tor for everything? How do you deal with the latency?

  20. comment
    Comment #46195747

    Nadella has to have his own custom agents. It isn't even possible for an enterprise like MSFT to not have custom agents that are still remotely useful. So, his experience with Copi…

  21. comment
    Comment #46025524

    @apwell23 while the author didn’t say how s/he measured QA, creating the QA process was literally the first bullet.

  22. comment
    Comment #46025493

    It’s easy to underestimate the amount of testing “just” prompt/context engineering takes to get above average results. And then you need to see what variations work best with diffe…

  23. comment
    Comment #45741240

    Seems like you answered your own question

  24. comment
    Comment #45105785

    Aren't all encyclopedias 'lossy'? They are all partial collections of information; none have all of the facts.

  25. comment
    Comment #44837118

    Azure AI Foundry says: How was the model trained? The gpt-oss models were pretrained primarily using synthetic data along with some heavily filtered real code. The models were then…