Live data from Hacker News

Viewing profile — mungoman2

mungoman2

HN member
Joined
Mon, Jul 14, 2014, 7:36 AM UTC
HN karma
463
Public activity
195 items

About mungoman2

No profile information was provided.

Recent public activity

  1. comment
    Comment #49234661

    Well, was the contract terminated? Saying no will sometimes have consequences, and the counterpart is sometimes unreasonable.

  2. comment
    Comment #48615031

    Similarly curious about this. The intuition I extracted: Let’s say we have 10 requests, where 9 of them take 1 second to complete but one that takes 100 seconds. The average time t…

  3. comment
    Comment #48486299

    In this case it could be solved by not letting the LLM consume the transaction message. Effectively the same as preventing user supplied info going to the first argument of printf(…

  4. comment
    Comment #48352690

    Curious about this take, how do you mean? I understand the point of distorted facts, but what I’m not sure how things are improved by basically having no trust in any facts?

  5. comment
    Comment #48321384

    This looks very interesting. Possible to get those rates without exotic hardware. But I have to say that the comparison is not really fair. Comparison is done with a 2 B model vs f…

  6. comment
    Comment #48166584

    Wow, this is really fascinating. And it reads like the intro of a sci-fi short.

  7. comment
    Comment #48094864

    This looks very cool, but it's not clear what it means. I wonder if it is captivating simply because it syncs cool graphics to audio, like those Winamp visualization filters in the…

  8. comment
    Comment #48072396

    Very interesting! Will definitely try this. Feedback: I think it would be beneficial to clarify that there is a trial at the top of the page. Currently we have download and buy but…

  9. comment
    Comment #48032628

    Naively it seems odd that running multiple checks in parallel is faster than just running the autoregressive model multiple times in series. It’s the same amount of compute right? …

  10. comment
    Comment #47886033

    This is an amazing idea, and congrats on getting so far through it. I personally would be wary about fire. Custom electronics without experience, and then putting (assuming here) h…

  11. comment
    Comment #47846469

    This is very interesting and exciting, but IMHO the comparisons read as a bit disingenuous with the other models at 16 bit weights. The 16 bit releases of the others models are not…

  12. comment
    Comment #47685783

    Instead of anchoring the sun and thus noon at the top it would be interesting to have the sun move around the clock face as the year progresses. Noon then moves around as the year …

  13. comment
    Comment #47514637

    What they're saying is that the error for a vector increases with r, which is true. Trivially, with r=0, the error is 0, regardless of how heavily the direction is quantized. Large…

  14. comment
    Comment #47486166

    This is cool. It makes storage of the KV cache much smaller, making it possible to keep more of it in fast memory. Bandwidth-wise it is worse (more bytes accessed) to generate and …

  15. comment
    Comment #47435704

    Well, the spec can of course define constraints of how the function is implemented.

  16. comment
    Comment #47408985

    Really good. I’ve struggled with the same thing. > Instead of expecting it to understand my requests, I almost always build tooling first to give us a shared language to discuss th…

  17. comment
    Comment #47364774

    Tbh shrinking the image is probably the cheapest operation you can do that still lets every pixel influence the result. It’s just the average of all pixels, after suitable color co…

  18. comment
    Comment #47280427

    This is a very fun idea. Would also be very interesting to see if one could have a system where talking to an NPC could alter the world. One maybe obvious way would be that asking …

  19. comment
    Comment #47252027

    Not sure what the uptime is meant to signal. People have quite low uptime as well…

  20. comment
    Comment #47228977

    I think you’re implying that it would be useful to have the LLM predict the end of the speaker’s speech, and continue with its reply based on that. If, when the speaker actually st…

  21. comment
  22. comment
    Comment #46945841

    But renewable is already cheaper than fossil fuels. Why don't we see this already?

  23. comment
    Comment #46935251

    IMHO, this is not really about AI, it's about setting boundaries and not overwork yourself.

  24. comment
    Comment #46853038

    Good article. Would have liked to see them create a minimal test case, to conclusively show that the results of math operations are actually incorrect.

  25. comment