Live data from Hacker News

Viewing profile — maxwells-daemon

maxwells-daemon

HN member
Joined
Wed, Sep 23, 2020, 9:16 PM UTC
HN karma
405
Public activity
50 items

About maxwells-daemon

I'm a machine learning researcher at Harmonic (ex-NVIDIA) working on automated theorem proving.

Site: https://aidanswope.com/ Email: aidanswope@gmail.com

Recent public activity

  1. comment
    Comment #49172528

    Funny enough, I had some valuable stuff (including my passport!) stolen from my car, which I'd left unlocked because I was moving some heavy boxes. The police in my area (bay area)…

  2. comment
    Comment #49014973

    As someone who also used to overthink memorizing the fretboard: this is a bad idea. You should strive to just plainly memorize the names of all of the notes, the relevant scale and…

  3. comment
    Comment #48140735

    I have exactly the same problem in my (latest-model) Honda Civic / Android Auto! I thought I was going crazy, I'm glad to hear someone else has the same problem. The only fix I've …

  4. comment
    Comment #47280360

    It's true, but most of the cultural innovation I'm aware of, from Bach to Coltrane to Hendrix, came from people who could make art their life, largely by paying the bills with it. …

  5. comment
    Comment #47277885

    That isn't how it works. Jimi Hendrix, the Beatles, and most other innovators were regular working artists long before they were influential. If you take away the means for artists…

  6. comment
    Comment #46562018

    Aristotle's output is formally verified in Lean, so you can run it for days on a hard problem and be assured that the answer, no matter how complex, is right without needing to man…

  7. comment
    Comment #46561996

    Yes! I think that working with Mathlib is the best long term solution, because it's how people already collaborate on building out the formal "universe of mathematics." We want to …

  8. comment
    Comment #46561983

    For this reason, when we announce results on e.g. the IMO, we formalize the statements by hand and inspect the proofs carefully to ensure they capture the full spirit of the proble…

  9. comment
    Comment #46561969

    Thank you! It depends on the topic. Some fields (algebra, number theory) are covered well by Lean's math library, and so I think we are already there; I recommend trying Aristotle …

  10. comment
    Comment #46561932

    We are! We very recently announced some results on formally proving the correctness of programs: https://harmonic.fun/news#blog-post-verina-bench-sota Formal methods are cool becau…

  11. comment
    Comment #46561569

    I work at Harmonic, the company behind Aristotle. To clear up a few misconceptions: - Aristotle uses modern AI techniques heavily, including language modeling. - Aristotle can be g…

  12. comment
    Comment #46298951

    There are a couple of interesting benefits from the machine learning side that I think discussions of this kind often miss. (This has been my field of research for the last few yea…

  13. comment
    Comment #42806761

    Maybe there's a middle ground: a site that wants to work as well as possible for agents could present a stripped-down standardized page depending on the user agent string, while th…

  14. comment
    Comment #41102730

    LeanDojo (at least as original published) did not use automatically formalized data, but extracted examples from Mathlib, which is already written in Lean.

  15. comment
    Comment #41097765

    Second author here. Happy to answer any questions about the work!

  16. comment
    Comment #31197266

    Wow! The ability to ingest the "cross product" of data on the internet and in the real world is huge; I bet a lot of what LMs don't know yet lives in that space. This seems a lot m…

  17. comment
    Comment #31100260

    In general, a function approximation solution like deep learning does worse on cases where exhaustively finding the exact optimum is possible (small combinatorial problems), but ca…

  18. comment
    Comment #31100199

    I guess so, but the fact of the matter is that ML/AI is actually, right now, doing useful things that would have been impossible 10 years ago. I don't think I could say the same ab…

  19. comment
    Comment #31100156

    Yes, the way I see it, one of the major benefits of deep learning is that it lets you define functions (in the R^n -> R^m sense) that would be basically impossible to define with t…

  20. comment
    Comment #31093923

    I work on this team! (Specifically: applied deep learning research, chip design). It's a shame to see so many people dismissing this work as marketing. I see lots of clever people …

  21. comment
    Comment #29517395

    Automated theorem proving + neural language models + reinforcement learning. I think most people seriously underestimate how powerful modern proof assistants like Lean [1] are for …

  22. comment
    Comment #29108845

    A friend who works in climate modeling recently told me that the best models currently in use pretty much all agree about the next few years, but they seriously diverge after a cou…

  23. comment
    Comment #28862432

    Caltech, right? Were you the author of Flippy? There's a new generation of AlphaZero-style ML bots that's managed to finally dethrone it :) I've been working on and off on a Rust O…

  24. comment
    Comment #28830890

    In my experience: one of Lean's main advantages is developer experience. It's convenient by design, with lots of automation to make easy proofs trivial. You do your work in VSCode …

  25. comment
    Comment #28670265

    I use 2x3090 to train large language models, and mine don't thermal-throttle with air cooling even though they're right next to each other. Eth mining does generate too much heat t…