Why don't machine learning research agents overfit?

View article

56 points by Betelbuddy 2 hours ago on hackernews | 29 comments

dominotw | 2 hours ago

> Machine learning, at its core, is about generalization, not memorization.

Well they memorize the patterns.

memorization doesnt mean rote learning.

: porridgeraisin | an hour 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.
: tomrod | an hour 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

demibabs | an hour ago

Even tech giants are putting out articles seemingly fully written by Claude.

ks2048 | an hour ago

The animated graphic labeled "Occam's razor, formalized" is bizarre. Is that really visualizing "Occam's razor, formalized"?

: mrbungie | an hour 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 | 53 minutes ago
I was expecting Occam wearing a suit.

serial_dev | 56 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...

cj | 50 minutes ago

What I really dislike is having to edit my own non-LLM assisted writing to make sure I'm not accidentally confused with AI.

I caught myself writing "And that matters because..." in a HN comment but had to edit myself. Also miss uising emdashes.

bee_rider | 36 minutes ago

These models are trained on human language, which belongs to us, we shouldn’t surrender it to them. Keep the em-dashes. IMO don’t overuse negative parallelisms though, they were always bad and lazy.

: srean | 20 minutes ago
An arms race on style would be interesting. Essentially a real life GAN.

percentcer | 17 minutes ago

Nobody wants to work anymore!

dguest | an hour ago

arXiv link: https://arxiv.org/abs/2606.11045

: gwern | 21 minutes ago
The methodology is partially based on https://www.offconvex.org/2021/04/07/ripvanwinkle/ , for those thinking this sounded familiar.

diddid | an hour 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 | 58 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.

: neutronicus | 42 minutes ago
Damn no wonder she got a supercomputer named after her
: diddid | 20 minutes ago
But I still don’t think that means eat all the cookies in the cookie jar and then apologize after because nobody would have given permission. That’s still about doing what you believe to be right. She even frames the fallout as “where you supposed to do that?” and not “you shouldn’t have done that”.

sillyfluke | 45 minutes ago

>It’s just like the Hopper quote.

Not sure about Hopper, as I recall biographers of Lawrence of Arabia certainly made it seem like he was using the fog of war to do things he knew his superiors may object to.

Regardless, even if its misinterpreted it still has a kernal of truth and separate utility than your version, that is: the people in the field closest to the action have an operational awareness that may result in better decisions in times of urgency.

beckhamc | 35 minutes ago

And sadly, in academia, complexity (opposite of Occam's razor) is what gets you published.

srean | 34 minutes ago

I think you should get less annoyed.

> It’s not that the simplest is more likely to be correct, it’s that you should prefer it, because it’s simple.

I don't know what Occam meant, but if you accept the formalism of PAC learning, it is more likely to be correct

http://www.cse.buffalo.edu/~hungngo/classes/2008/694/papers/...

http://cs.ecs.baylor.edu/~hamerly/courses/5325_10s/papers/le...

: p-e-w | 26 minutes ago
There are also various metaphysical theories that posit that the universe is algorithmically generated in some sense or the other, and from many of those theories it follows that simplicity is a fundamental feature of reality, which yields an even stronger version of Occam’s Razor.
: ruszki | 3 minutes ago
None of your links work for me.

nyeah | an hour ago

They tend not to overfit ... when there are way more data points than parameters.

: wmedrano | 56 minutes ago
Or when there are way more parameters than data points
https://en.wikipedia.org/wiki/Double_descent

32df179 | an hour 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.

vatsachak | 23 minutes ago