Why don't machine learning research agents overfit?

(amazon.science)

36 points | by Betelbuddy 1 hour ago

7 comments

  • demibabs 48 minutes ago
    Even tech giants are putting out articles seemingly fully written by Claude.
    • ks2048 33 minutes ago
      The animated graphic labeled "Occam's razor, formalized" is bizarre. Is that really visualizing "Occam's razor, formalized"?
      • mrbungie 23 minutes ago
        Ah, over-the-top larger-than-life LLM-isms, they are really funny when you see them in a company blog, but they are vomitive when it's your coworker copy-pasting it and insisting you on reading it.
      • smashah 3 minutes ago
        I was expecting Occam wearing a suit.
    • serial_dev 6 minutes ago
      Time to first detected slop in this article is <1s. Claudisms per paragraph is also very high.

      Is it too much to ask from people to read their own article anymore?

      If anyone read this at all, they would have had the ick, and would have fired off a prompt to get rid of the most popular AI slop tells...

  • diddid 17 minutes ago
    I always get annoyed when people misinterpret Occam’s razor. It’s not that the simplest is more likely to be correct, it’s that you should prefer it, because it’s simple.

    It’s just like the Hopper quote. She said it’s better to ask for forgiveness during the fog of war, doing something you thought was right, not to do something you knew they were going to say no to and now you are trying to get away with something.

    • gowld 8 minutes ago
      That's not true. It's pretty clear that she meant "do something you knew they were going to say no to and now you are trying to get away with something."

      https://youtu.be/wHdHCoeUbU4?t=861s

      > So I want to tell something to all the young people here on many many occasions you'll find it is much easier to apologize than it is to get permission. You do it then when somebody comes after you and say are you supposed to do that, "oh gee I didn't know I wasn't supposed to do that" ... so just remember it's frequently much easier to apologize than it is to get permission do it

      She goes on further, explaining how to deceive your superiors to manipulate them to get what you want.

  • nyeah 16 minutes ago
    They tend not to overfit ... when there are way more data points than parameters.
  • dguest 28 minutes ago
  • 32df179 13 minutes ago
    Wherein Claude gives an honest assessment that it genuinely does not overfit. I also had Grok telling me that it isn't quantized.

    Do the submitters really not notice that this is AI slop? Do they like this? It is a complete pain to read.

  • novaapi 20 minutes ago
    [flagged]
  • dominotw 1 hour ago
    > Machine learning, at its core, is about generalization, not memorization.

    Well they memorize the patterns.

    memorization doesnt mean rote learning.

    • tomrod 13 minutes ago
      I don't take issue with that. Attempting memorized pattern generalization through holdout / validation strategies is a big part of ML that you would not typically see with econometrics / psychometrics / possibly sabermetrics / most other -metrics. Philosophically the explain versus predict divide. https://www.stat.berkeley.edu/~aldous/157/Papers/shmueli.pdf
    • porridgeraisin 13 minutes ago
      That's a bit pedantic no. Memorization in ML refers to the model having the wrong level of capacity such that it's too hard to optimise it such that it doesn't memorize the _training examples_ themselves.