Live data from Hacker News

Viewing profile — goggy_googy

goggy_googy

HN member
Joined
Wed, Feb 21, 2024, 10:46 PM UTC
HN karma
9
Public activity
12 items

About goggy_googy

No profile information was provided.

Recent public activity

  1. comment
  2. story
  3. comment
    Comment #40300853

    What makes this such a "deeply broken situation"? I agree that late-stage capitalism can create really tough situations for poor families trying to afford drugs. At the same time, …

  4. comment
    Comment #40300545

    I think at some point, we will be able to produce models that are able to pass data into a target model and observe its activations and outputs and put together some interpretable …

  5. comment
    Comment #40300498

    Agreed. At the very least, models of this nature let us iterate/filter our theories a little bit more quickly.

  6. comment
    Comment #40227168

    No, the activations are a combination of the basis function and the spline function. It's a little unclear to me still how the grid works, but it seems like this shouldn't suffer a…

  7. comment
    Comment #40148099

    [flagged]

  8. comment
    Comment #40148051

    I think the hand running through the wheat (?) is pretty good, object permanence is pretty reasonable especially considering the GAN architecture. GANs are good at grounded generat…

  9. comment
    Comment #39843169

    Reminds me a little bit of a bloom filter in its functionality

  10. comment
    Comment #39485767

    This paper reminds me of the Neural Network Diffusion paper which was on the front page of HN yesterday in the sense that we are training another model to bypass a number of iterat…

  11. comment
    Comment #39460756

    "We synthesize 100 novel parameters by feeding random noise into the latent diffusion model and the trained decoder." Cool that patterns exist at this level, but also, 100 params m…

  12. comment
    Comment #39460687

    Important to note, they say "From these generated models, we select the one with the best performance on the training set." Definitely potential for bias here.