Live data from Hacker News

Viewing profile — sc077y

sc077y

HN member
Joined
Mon, Jan 02, 2023, 11:04 AM UTC
HN karma
89
Public activity
34 items

About sc077y

Software Engineer, currently working in genAI.

I'm just a student of the game.

Recent public activity

  1. comment
    Comment #49081212

    A lot of the heads of AI labs are talking about this including Dario, Demis and ELon, they are seeking to do a sort of decentralized peer review system, where the competitors have …

  2. comment
    Comment #49057435

    All the AGI (which is a misnomer, ASI is preferred) talk is about the moment of singularity, which is where the growth at the third derivative is increasing, so the gap (in the abs…

  3. comment
    Comment #46253691

    Who knew that English would be the most popular programming language of 2025?

  4. comment
    Comment #46025601

    73% of statistics are wrong

  5. comment
    Comment #44955082

    I believe the ARC-AGI benchmark fits that description, it's sort of an IQ test for LLMs, though I would caution against using the word "Intelligence" for LLMs.

  6. comment
    Comment #44914802

    Woz is just a nerd, simple as that. And he stayed true to himself and that ethos his whole life.

  7. comment
    Comment #44776762

    Every time you use these tools irresponsibly, for instance for what I like to call headless programming (vibe coding), understand that you are incurring tech debt. Not just in term…

  8. comment
    Comment #44776729

    Critical Skills is spotting the potential bugs before they happen but in order to do that you need to have an extremely acute understanding or a have a lot of experience in the sta…

  9. comment
    Comment #44742037

    In that case, you use copy OR what you can can also do, if you really care about disk usage, is use symbolic links between the drives. have a .venv sym link on drive A (raid 1) poi…

  10. comment
    Comment #44739670

    I tried installing and setting up the project today, it was miserable. I finally got it to work only to find out that the mistral models' tool calling does not work at all for clau…

  11. comment
    Comment #44708153

    I recently saw an interview without someone on the mac team and what's interesting is that the original Mac team had a lot of friction because of this philosophy. Jobs constantly a…

  12. comment
    Comment #44649461

    By default it will create hard links for python packages, so it won't consume any more memory (besides the small overhead of hard links).

  13. comment
    Comment #44649017

    I tried Multi-Account Containers to try isolate my work from my personal but it just wasn't good enough. History, bookmarks, passwords and plugins were all shared. Do I really need…

  14. comment
    Comment #43692825

    I'm wondering if one of the big reasons that OpenAI is making gpt-4.5 deprecated is not only because it's not cost-effective to host but because they don't want their parent model …

  15. comment
    Comment #43595236

    DocLayout-YOLO model is under the AGPL-3.0 license, it's not permissive. You can't have your project under the MIT license and also use copyleft software.

  16. comment
    Comment #43409421

    The problem I see with this definition is that we have things called RAG agents which don't technically act in any environment except for provide information.

  17. comment
    Comment #42713483

    The way that the embedding is done is using Matryoshka Representation Learning, truncating it allows to compress while losing as little meaning as possible. In some sense it's like…

  18. comment
    Comment #42585953

    Actually the rate of hallucination is not constant across the board. For one you're doing a sort of synthesis, not intense reasoning or retrieval with the llm. Second, the problem …

  19. comment
    Comment #42585594

    Given that it's a French company I can almost guarantee that it was written/translated using an LLM.

  20. comment
    Comment #41319526

    This is impressive, it's hard to imagine all the implications of a BMI.

  21. comment
    Comment #41308408

    The real question here is who puts their API keys on a slack server ?

  22. comment
    Comment #40750034

    Damn I built a RAG agent during the past 3 months and a half for my internship. And literally everyone in my company was asking me why I wasn't using llangchain or llamaindex like …

  23. comment
    Comment #40680271

    Shkreli has actually sent the album to various people. He used to used to send it to any girl who asked for it back in the day. It's not that exclusive. Also according to Martin, n…

  24. comment
    Comment #40644046

    I'm skeptical of the on-device AI. They crave edge compute but I'm doubtful their chips can handle a 7B param model. Maybe ironically with Microsoft's phi 3 mini 4k you can run thi…

  25. comment
    Comment #40644013

    Impressive not technically because nothing here is new but because it's the first real implementation for the average end consumers of "ai". You have semantic indexing which allows…