Live data from Hacker News

Viewing profile — fxnn

fxnn

HN member
Joined
Tue, Jan 31, 2023, 9:58 PM UTC
HN karma
12
Public activity
15 items

About fxnn

Software Developer Java, Go, Bash, k8s, … https://fxnn.de

Recent public activity

  1. comment
    Comment #47113953

    We can expect the model landscape to consolidate some day. Progress will become slower, innovations will become smaller. Not tomorrow, not next year, but the time will come. And th…

  2. comment
    Comment #47113894

    Read the blog post. It mentions that their chip has a small SRAM which can store LoRA.

  3. comment
    Comment #44426803

    No, it did not mostly refer to to-do lists. At least that's not what I understood. It was an example, yes. But he also referred to Luhmann’s Zettelkasten, a huge collection of note…

  4. comment
    Comment #44163093

    That's one thing where I love Golang. I just tell Aider to `/run go doc github.com/some/package`, and it includes the full signatures in the chat history. It's true: often enough A…

  5. comment
    Comment #43440854

    The author would be excited to learn that CouchDB solves this problem since 20 years. The use case the article describes is exactly the idea behind CouchDB: a database that is at t…

  6. comment
    Comment #42612718

    Even if I don’t care much about the „digital garden“ concept, I was much surprised to visit a page called „blogscroll“, click on a link, and then not find a blog.

  7. comment
    Comment #42248388

    > When we talk about understanding a simple axiomatic system, understanding means exactly that the entirety of the axioms are modeled and applied correctly 100% of the time. Yes, b…

  8. comment
    Comment #42014995

    Maybe it needs even smaller steps, and a programmatic (i.e. multi prompt) habit to always double-check / validate the assumptions and outcomes.

  9. comment
    Comment #37411081

    But that also exists in the AI world. It’s called „fine tuning“: a LLM trained on a big general dataset can learn special knowledge with little effort. I’d guess it’s exactly the s…

  10. comment
    Comment #37411038

    Hmm. You sure this is the same thing? I would say it’s more about confidentiality than about value. Because what companies want to hide are usually secrets, that are available to (…

  11. comment
    Comment #37309444

    Okay if it’s about looking at one painting and fake that. However, if you train your model on billions of paintings and create arbitrary new ones from that, it’s just a statistical…

  12. comment
    Comment #37309207

    Okay, so the scale at which they sale their service is a good argument that this is different from a human learning. However, on the other hand we also have the scale at which they…

  13. comment
    Comment #37304797

    For me that discussion is always hard to grasp. When a human would learn coding autodidacticly by reading source code, and later they would write new code — then they could only do…

  14. comment
    Comment #37304768

    Sounds like the perspective of someone who never gave that tool a real chance. To me it’s primarily just another aid like IDE inspections, IDE autocompletions etc. I use GitHub Aut…

  15. comment
    Comment #34602944

    Highly recommending Martin Kleppmanns „Designing Data-Intensive Applications“ book (O‘Reilly). Covers virtually any topic around database implementation. Well written, big source o…