Live data from Hacker News

Viewing profile — dandelionv1bes

dandelionv1bes

HN member
Joined
Tue, Aug 12, 2025, 8:44 AM UTC
HN karma
35
Public activity
41 items

About dandelionv1bes

No profile information was provided.

Recent public activity

  1. comment
    Comment #46932781

    If you’re interested in an easy explainer for backprop, then highly recommend math for deep learning by Kneusel. Finished it recently and you can apply the chain rule backwards by …

  2. comment
    Comment #46834849

    Saw Empire of AI in a bookshop recently but held off buying as wasn’t sure if it was going to be surface level. You’d recommend?

  3. story
  4. story
  5. comment
    Comment #46690476

    I struggle with this a bit because while my network isn’t bad - I really can’t stand social network like threads/X etc - I’m not on any social media bar here and LinkedIn. Do you t…

  6. comment
    Comment #46668174

    Nice read - I can’t seem to subscribe? Getting an error with Buttondown.

  7. story
    Show HN: Tiny Toy Network – a neural net to practice backpropagation

    I’ve recently finished Math for Deep Learning and really enjoyed computing back propagation by hand. However, it’s one of those things where if you stop doing it for six months, yo…

  8. comment
    Comment #46666205

    i’m sorry this really made me laugh - I hope she’s ok!

  9. comment
    Comment #46657025

    I think the docs are great to read, but implementing was a completely different story for me, ie, the Ask AI recommended solution for implementing Claude just didn’t work for me. T…

  10. comment
    Comment #46656961

    I do understand why it’s a product - it feels a bit like what databricks has with model artifacts. Ie having a repo of prompts so you can track performance changes against is good.…

  11. comment
    Comment #46629986

    I’ve been slowing crunching through Math for Deep Learning, so spent a fair amount of time looking at Hessian matrices + second order optimisation. I’ve been slowly reading this bo…

  12. story
    Show HN: Llama 4 Maverick explores Japantown in Watch Dogs 2

    This is a little project we’ve been working on, which started as multimodal models physically controlling gamepads. It’s evolved a little bit since then and we now have a setup whe…

  13. story
  14. comment
    Comment #46564587

    Amazing! Thanks will join.

  15. comment
    Comment #46564376

    This is fantastic. I think it’s nailed in the substack what was missing from a lot of these LLM driven NPCs that did not feel authentic. I have a couple of follow-up questions on s…

  16. comment
    Comment #46564348

    GAMM in Rome is quite fun (Italy): https://www.gammuseum.com/en/ Shout-out to the museum of Ancient Greek technology, with their wine automaton (Athens, Greece): https://kotsanas.c…

  17. comment
    Comment #46564339

    Bletchley is great! I need to go again

  18. comment
    Comment #46510140

    Haven’t seen Wiby before but it’s fantastic, thank you.

  19. comment
    Comment #46505910

    The response to the Sal Khan op-ed resonated with me, along with other parts of this article. Something I’ve been digging more into is some of the figures around proposed job losse…

  20. comment
    Comment #46505785

    Thank you for putting it together. I looked at a couple of the references and they look like they point to your blog. Do you have a view at all of popular patterns in terms of cita…

  21. comment
    Comment #46496637

    I thought Gas Town was a satire until I saw the GitHub. Maybe it’s a very involved satire? It is right? “ Do not use Gas Town.”

  22. story
  23. story
  24. comment
    Comment #46400717

    Catch 22 is just fantastic isn’t it. I might re-read in 2026!

  25. comment
    Comment #46334806

    Something I’ve been thinking about is how as end stage users (eg building our own “thing” on top of an LLM) we can broadly verify it’s doing what we need without benchmarks. Does a…