Live data from Hacker News

Viewing profile — taf2

taf2

HN member
Joined
Thu, Jul 15, 2010, 2:45 AM UTC
HN karma
3,802
Public activity
2,040 items

About taf2

CTM

Recent public activity

  1. comment
    Comment #49226497

    As a business though I can spend 100k and run this model and support about 10 fte- not bad…

  2. comment
    Comment #49225236

    Got this up and running at 250 tok/s about 2500 agg tok/s for 16 users and now this morning got https://huggingface.co/webbrain-one/DeepSeek-V4-Flash-0731-V... working - patched it…

  3. comment
    Comment #49222918

    we got this running on 4 RTX Pro 6000's and for single request we're getting around 250 tok/s we can support about 48 concurrent requests we're seeing around 2400 agg tok/s peaking…

  4. comment
    Comment #49156036

    Llm are great at things that are repeatable. Otherwise they are just like us - great at believable bullshit… a sign of true intelligence

  5. comment
    Comment #49117990

    I remember bugs always end up being more expensive then the first time I implemented the feature… so for me always sol always max… I don’t want to pay for a bug later

  6. comment
    Comment #49116094

    yeah i can't say if it's 2x or 10x or 100x i don't know. i just know i barely open vim anymore. I still find my rate of development is limited by how much my single mind can hold a…

  7. comment
    Comment #49070982

    404 is resolved let the downloads begin

  8. comment
    Comment #49070527

    it's a 404 link now

  9. comment
    Comment #49038664

    eager to see how it benchmarks on https://deepswe.datacurve.ai/

  10. comment
    Comment #49005135

    August 2025 for me but now days I’m much more extreme- it does it all max sol in mornings and then I do other things in the afternoon. I get more done than before with far less str…

  11. comment
    Comment #48999873

    Would love to see the results if they had used /goal or similar

  12. comment
    Comment #48937164

    I'm not finding this on huggingface yet is and open model or is kimi now a closed model ?

  13. comment
    Comment #48876727

    [flagged]

  14. comment
    Comment #48834304

    Not finding anything about this while searching huggingface: https://huggingface.co/search/full-text?q=SWE-1.7 i assume this is another closed source model?

  15. comment
    Comment #48806774

    i love the built in AI - i created this tic tac toe game with an AI trash talking opponent -> https://taf2.github.io/ai-tic-tac-toe-trash-talk/

  16. comment
    Comment #48788872

    The timescale of this analysis is a big issue IMO- Covid hiring was all kinds of whacked out - with FANG companies competing to hire literally entire graduating cs classes.

  17. comment
    Comment #48746197

    this gives me children of time vibes

  18. comment
    Comment #48727422

    Best way to make your M series macbook pro feel like a good old fashion intel macbook pro. Run a local model.

  19. comment
    Comment #48546453

    when i read "keys" i figured "names" like in my .ssh/config a named host that i access with a key... but listening more it sounds like a new way to do networking over QUIC...

  20. comment
  21. comment
    Comment #48469391

    I’m waiting to see results on deepswe - that benchmark really seemed accurate for opus and gpt 5.5…

  22. comment
    Comment #48370685

    I wanted to love flux.ai because i love codex... and if i could automate the creation of some PCB projects with as much success as I am with codex it would have been quiet fun in t…

  23. comment
    Comment #48205588

    That sucks I guess I won’t be using any Google llms anymore

  24. comment
    Comment #48136861

    are there any stats pointing to these students going to different schools? we know birth rates fell sharply starting ~2008 and have stayed low. [ https://www.cdc.gov/nchs/data/vsrr…

  25. comment
    Comment #48035472

    4gb? Maybe on a raspberry pie it’s a problem - I’m sure there is a chrome flag to disable