Live data from Hacker News

Viewing profile — pash

pash

HN member
Joined
Sat, May 28, 2011, 3:00 AM UTC
HN karma
3,397
Public activity
480 items

About pash

I do quant-finance and ML things, write Haskell, and ride bicycles. I also do other things, but less often.

Recent public activity

  1. comment
  2. story
  3. story
  4. comment
    Comment #48342007

    Right, that’s why I wrote, “I don’t mean that most neural networks are invertible functions.” For a neural network that is not bijective, you can obtain an input that maps to a des…

  5. comment
    Comment #48332819

    The obvious solution is to run things in reverse, inputting the AI-generated output to recover the prompt that generated it. Most generative models can be run in reverse by algorit…

  6. comment
  7. comment
    Comment #47896190

    The inflection point was 2012, when AlexNet [0], a deep convolutional neural net, achieved a step-change improvement in the ImageNet classification competition. After seeing AlexNe…

  8. comment
    Comment #47788826

    https://en.wikipedia.org/wiki/Sprezzatura https://en.wikipedia.org/wiki/Wabi-sabi

  9. comment
  10. comment
    Comment #47328953

    > Even for billion-parameter theories, a small amount of vectors might dominate the behaviour. We kinda-sorta already know this is true. The lottery-ticket hypothesis [0] says that…

  11. comment
    Comment #47302271

    Sandvault [0] (whose author is around here somewhere), is another approach that combines sandbox-exe with the grand daddy of system sandboxes, the Unix user system. Basically, give…

  12. comment
  13. comment
  14. comment
    Comment #47185250

    OK, let’s survey how everybody is sandboxing their AI coding agents in early 2026. What I’ve seen suggests the most common answers are (a) “containers” and (b) “YOLO!” (maybe addin…

  15. comment
    Comment #46985097

    Milton Friedman wouldn’t have approved of a basic-income scheme restricted to artists. He would have argued that restricting the benefit to artists would distort incentives for cho…

  16. comment
  17. comment
    Comment #46573893

    From what I understand, which is very incomplete, the leading hypothesis at the moment is that ingested prions are a bit hard to digest (because they’re malformed proteins), so the…

  18. comment
    Comment #46573374

    I’m not qualified to comment intelligently on what might be going on here, but I’d like to add some background color that the article lacks. Creutzfeldt–Jakob Disease is a prion di…

  19. comment
    Comment #46156870

    Philip E Converse, The Nature of Belief Systems in Mass Publics (1964), 75 pages [0]. 0. https://web.ics.purdue.edu/~hoganr/Soc%20312/The%20nature%20... [PDF]

  20. comment
  21. story
  22. comment
    Comment #45320231

    > We should be able to define our functions to accept the inputs they are designed for, and not try to handle every possible edge case. Oh, look, somebody just re-discovered static…

  23. comment
  24. comment
  25. story