Live data from Hacker News

Viewing profile — brrrrrm

brrrrrm

HN member
Joined
Tue, Feb 09, 2021, 1:20 AM UTC
HN karma
2,120
Public activity
566 items

About brrrrrm

http://twitter.com/bwasti

http://github.com/bwasti

[all posted thoughts and comments are my own]

Recent public activity

  1. comment
    Comment #49252353

    are these all uniform quantization? or mixed and matched by layer (can't tell from the naming scheme)

  2. comment
    Comment #49164178

    this is cool but like, are we just vibe coding NAND burners at this point? these decode times don't really tell the whole story, because prefill becomes the bottleneck. half an hou…

  3. comment
    Comment #49134915

    there's wifi ah, which runs on 900mhz band and has the same 30dbm limitation I've used it with some raspberry pis to create hi-fidelity walkie talkies it's quite pleasant.

  4. comment
    Comment #49019419

    Models are increasingly showing their ability to extrapolate into the human unexplored (math proofs being the most apparent). What gives you confidence the absurdity of life is uni…

  5. comment
    Comment #48921821

    > you are basically looking at a whole system prompt just describing the new language whats wrong with this? You may be over-indexing on the need for large quantities of examples. …

  6. comment
    Comment #48734006

    it's very much an in-domain term for folks in machine learning. heavily used when pipeline parallelism caught on in training https://alband.github.io/doc_view/pipeline.html

  7. comment
    Comment #48271860

    it has paddle shifters - what are those for?

  8. comment
    Comment #48091022

    what's MRT?

  9. comment
    Comment #48023400

    same can be said for a lot of things tho. e.g. nature used to be fun but then we discovered it all :’( I miss when ships literally sailed into the unknown and found surprising and …

  10. comment
    Comment #48016972

    I agree fully. Hyundai has a mockup that starts to get there (different era, but same concept) called the N vision 74[1], but I doubt we'll see it in market anytime soon. The unfor…

  11. comment
    Comment #47753361

    meta.ai in instant mode gets it first try too (I think?) ``` 2x + y = \operatorname{eml}\Big(1,\; \operatorname{eml}\big(\operatorname{eml}(1,\; \operatorname{eml}(\operatorname{em…

  12. comment
    Comment #47685220

    you're right, this is actually correctly placed! I was confusing the orientation. I live right around there and recognize the M&T bank in the photo on the left, so it can't be down…

  13. comment
    Comment #47678855

    I checked 3 spots I'm familiar with and 1 is wrong https://www.oldnyc.org/#707133f-a this is supposed to be here https://www.oldnyc.org/#702487f-a also, if folks are interested in …

  14. story
  15. story
  16. comment
    Comment #46363149

    looks cool! one bit of feedback: make your demo gif get to the point faster. either practice typing a bit quicker or speed it up 2x for the typing section

  17. story
  18. comment
    Comment #46126720

    on Bun's website, the runtime section features HTTP, networking, storage -- all are very web-focused. any plans to start expanding into native ML support? (e.g. GPUs, RDMA-type net…

  19. story
  20. story
  21. comment
    Comment #45883933

    we've discovered some kind of differentiable computer[1] and as with all computers, people have their own interests and hobbies they use them for. but unlike computers, everyone pi…

  22. comment
    Comment #45846581

    a recent wave of interest in bitwise equivalent execution had a lot of kernels this level get pumped out. new attention mechanisms also often need new kernels to run at any reasona…

  23. story
  24. story
  25. story