Live data from Hacker News

Viewing profile — dongecko

dongecko

HN member
Joined
Mon, Jul 29, 2019, 8:56 PM UTC
HN karma
21
Public activity
27 items

About dongecko

meet.hn/city/de-Bonn

Socials: https://github.com/gecko

Interests: AI/ML & Data Science, Hardware-Hacking, Gaming, Hardware, Electronics, Open Source, Philosophy, Programming, Research, Math, Science, Technology

---

Recent public activity

  1. comment
    Comment #47326309

    What a great read! You got me at the base64 oddity. I also stumbled over this, while trying to dodge some LLM limitation. (was trying to generate images in a time before multimodal…

  2. comment
    Comment #47285544

    Naaa, you have to think of the poster in options. Like, "would you want to have some extra publicity with your poster for an extra 100 bucks?"

  3. comment
    Comment #46607423

    I never realized; thanks for pointing that out. Sneakers is one of my favorite movies.

  4. comment
    Comment #46386770

    A while back, someone made https://meet.hn . It's a map where people from hackernews could locate themselves. Of course this is by far not comprehensive, but it gives you an idea o…

  5. comment
    Comment #45450512

    Exactly my point of view. For the most part I do not root for my preferred technology, but rather try to inform my powers about the caveats I see. This way at least the right aspec…

  6. comment
    Comment #43014325

    Yes, they can. Meta described a clever way in their paper on training Llama3 [1] (in section about factuality). The idea is to sample several answers to a question that you know th…

  7. comment
    Comment #42433282

    We have a couple of systems at work that incorporate LLMs. There are a bunch of RAG chatbots for large documentation collections and a bunch of extract-info-from-email bots. I woul…

  8. comment
    Comment #42163848

    Came here for exactly that. Thank you.

  9. comment
    Comment #41780724

    Bolzman machines were there in the very early days of deep learning. It was a clever hack to train deep nets layer wise and work with limited ressources. Each layer was trained sim…

  10. comment
    Comment #41776326

    This comment caught me off guard! I literally blew my coffee all over the table.

  11. comment
    Comment #41739235

    I second that thought. There is a pretty well cited paper from the late eighties called "Multilayer Feedforward Networks are Universal Approximators". It shows that a feedforward n…

  12. comment
    Comment #41085727

    Motorola used to have a one bit microprocessor, the MC14500B.

  13. comment
    Comment #41085685

    I simply love this book!

  14. comment
    Comment #39380689

    At the very beginning of my journey I did some fine tuning with Lora on a (I believe) Falcon model, but I haven't looked at it since. My impression was that injecting knowledge via…

  15. comment
    Comment #39380090

    I have not encountered this problem yet. When I was talking about the format of the answer I meant the following: No matter if you're using Langchain, Llamaindex, something self ma…

  16. comment
    Comment #39376607

    I also think of the retrieval part as a bottleneck and I am super excited of what the future holds. In particular, I wonder if RAG systems will soon be a thing of the past, because…

  17. comment
    Comment #39376467

    That is an interesting observation. I have not gotten to the point of too long cycles and I can think of two reasons for that. Maybe my use case is narrow enough, so that in combin…

  18. comment
    Comment #39374628

    The company I work for has tons of documentation and regulations for several areas. In some areas the documents are well over a thousand and for the ease of use of these documents …

  19. comment
    Comment #38776160

    I have been to a couple of hackathons as participant and as organizer. Some sessions where really good and some were really terrible. The biggest takeaway for me in organizing a ha…

  20. comment
    Comment #37370562

    I read it the same way as you did, or at least it's an approximation. In general that's not really surprising. I remember discussions from some years ago about larger networks lead…

  21. comment
    Comment #35030382

    There is also the evo64 project which rebuild the c64 with modern parts.

  22. comment
    Comment #33612043

    I love this thread. The question is so unspecific that it's like a version of "To get the right answer you need to post something wrong on the internet".

  23. comment
    Comment #33592501

    I think that the display is not used at all. If I understood correctly, the scart connector is hosting a hidden uart interface. This let's you connect a serial terminal via three c…

  24. comment
    Comment #33408303

    I use monokai and dracula, depending on the environment. If i can alter something, I usually go for dracula and FiraScript as font.

  25. comment
    Comment #32307382

    I really love this book. Beautiful data and beautiful visualizations are also nice reads, but beautiful code has a special place in my heart.