Live data from Hacker News

Viewing profile — SonOfLilit

SonOfLilit

HN member
Joined
Sat, Oct 06, 2007, 10:29 PM UTC
HN karma
2,714
Public activity
777 items

About SonOfLilit

CTO consultant

@AurSaraf sonoflilit at everyone's favorite email service

meet.hn/city/il-Tel-Aviv

Socials: - github.com/sonoflilit - linkedin.com/in/aursaraf

Interests: Climbing, Entrepreneurship, Fintech, Freelancing, Hacking, Open Source, Programming, Startups, Technology

---

Recent public activity

  1. comment
    Comment #49059165

    Huh? The wiktionary link I included links to (Failspy's message in) this 2024 discussion about how and when and why it was coined (by failspy): https://huggingface.co/posts/mlabonn…

  2. comment
    Comment #49050182

    Is there any evidence that would change your mind? The wiki "ablation" article you yourself linked dedicates a section to explain "abliteration". Googling abliteration arxiv yields…

  3. comment
    Comment #49045554

    I wnt and read your other comments. Except for the initial comment, they were aggressive and sometimes disrespectful claims that "the word is spelled ablation, here are some papers…

  4. comment
    Comment #49036196

    [flagged]

  5. comment
    Comment #49007183

    https://github.com/NousResearch/llm-abliteration

  6. comment
    Comment #48994382

    I understand basic multivariate calculus (almost every STEM degree teaches it, and I paid attention), which is enough to understand the problem if not every detail about the soluti…

  7. comment
    Comment #48990140

    The counterexample in the news cycle today helps better understand how the math works. I can't think of one that doesn't.

  8. story
    Show HN: How to Get a Fable CoT for the Jacobian Conjecture Refutation

    Since the publication of the Jacobian Conjecture refutation, many people have asked for a Chain of Thought to be published so they can better understand the mathematical intuition …

  9. comment
    Comment #48977391

    I think many long-haul truckers work in pairs for this reason?

  10. comment
    Comment #48975965

    By the CoT content, this is a screenshot of someone giving Fable the result and asking if it's true, not the CoT of discovery. e.g. "maybe the user's example is DESIGNED to be "cor…

  11. comment
    Comment #48965347

    Yes. You could say this is the sound of silence.

  12. comment
    Comment #48962717

    Apparently "onomatope" is a much less popular name for the same thing (e.g. Wikipedia uses my version). I mean that the "remove a word" 'symbol' is a 'word' that represents the ver…

  13. comment
    Comment #48960066

    It's an onomatopoeia

  14. comment
    Comment #48959958

    But to be fair, ZK proofs have strong "Cryptography 2: the Dark Tower" (2cryp2graphy?) vibes. The amount and level of power use of cryptography primitives and their minutiae is ins…

  15. comment
    Comment #48959865

    I didn't dive into the technical details of how pairing works, and in fact leared everything I know about it from TFA, which went into quite some detail.

  16. comment
    Comment #48952900

    TL;DR imagine a signature verification library that verifies a signature indeed signs the given hash, but not that the signed data hashes to that hash. Woopsie. I guess nobody's co…

  17. comment
    Comment #48952728

    It's a "this transaction is valid even though the signatures, amounts, potentially everything is wrong about it" vuln. Every node that uses this library to validate would lose sync…

  18. comment
    Comment #48840738

    This is not interesting in the way that "DNS parsing is turing complete" is interesting. Nobody can send you a unicode file and make you run an infinite loop or whatever. Within Un…

  19. comment
    Comment #48826096

    I hesitated to recommend the CEV paper, because it's written in Yudkowsky's very personal tone, which some enjoy and others find quite abrasive... but then it occurred to me that y…

  20. comment
    Comment #48807810

    The "OG" alignment research that MIRI were publishing long before LLMs burst into the scene spent most of it's time on that question. "How can we even define what an aligned AI sho…

  21. comment
  22. comment
    Comment #48666698

    But it is full of "not x, but y", just not above the fold... Probably many noticed and nobody wanted to spam with the complaint, I decided the spam is worth it for the author to ge…

  23. comment
    Comment #48651122

    Thanks. Claude tells me the essense of this example is "the GA formula for rotation works in 4D (vs quaternions), and to do something like rotation in kD you need a tuple of two ob…

  24. comment
    Comment #48646503

    I started keeping my eyes open when the wrong season was given for the Bad Place spoiler (I see this was since corrected, and maybe the flow there was improved as well?). In the fi…

  25. comment
    Comment #48643251

    I wish I could just read the prompt rather then the very long article full of tiny mistakes that was generated from it.