←back to thread

An image of an archeologist adventurer who wears a hat and uses a bullwhip

(theaiunderwriter.substack.com)
1503 points participant3 | 4 comments | 03 Apr 25 17:55 UTC | HN request time: 0.001s | source
Show context
MgB2 ◴[03 Apr 25 20:24 UTC] No.43574927[source]▶
Idk, the models generating what are basically 1:1 copies of the training data from pretty generic descriptions feels like a severe case of overfitting to me. What use is a generational model that just regurgitates the input?

I feel like the less advanced generations, maybe even because of their limitations in terms of size, were better at coming up with something that at least feels new.

In the end, other than for copyright-washing, why wouldn't I just use the original movie still/photo in the first place?

replies(13): >>43575052 #>>43575080 #>>43575231 #>>43576085 #>>43576153 #>>43577026 #>>43577350 #>>43578381 #>>43578512 #>>43578581 #>>43579012 #>>43579408 #>>43582494 #
ramraj07 ◴[04 Apr 25 04:40 UTC] No.43578381[source]▶
So I train a model to say y=2, and then I ask the model to guess the value of y and it says 2, and you call that overfitting?

Overfitting is if you didn't exactly describe Indiana Jones and then it still gave Indiana Jones.

replies(2): >>43578447 #>>43579929 #
MgB2 ◴[04 Apr 25 04:51 UTC] No.43578447[source]▶
The prompt didn't exactly describe Indiana Jones though. It left a lot of freedom for the model to make the "archeologist" e.g. female, Asian, put them in a different time period, have them wear a different kind of hat etc.

It didn't though, it just spat out what is basically a 1:1 copy of some Indiana Jones promo shoot. No where did the prompt ask for it to look like Harrison Ford.

replies(3): >>43578572 #>>43582523 #>>43585657 #
fluidcruft ◴[04 Apr 25 05:14 UTC] No.43578572[source]▶
But... the prompt neither forbade Indiana Jones nor did it describe something that excluded Indiana Jones.

If we were playing Charades, just about anyone would have guessed you were describing Indiana Jones.

If you gave a street artist the same prompt, you'd probably get something similar unless you specified something like "... but something different than Indiana Jones".

replies(2): >>43578848 #>>43579133 #
1. 9dev ◴[04 Apr 25 06:11 UTC] No.43578848{3}[source]▶
And… that is called overfitting. If you show the model values for y, but they are 2 in 99% of all cases, it’s likely going to yield 2 when asked about the value of y, even if the prompt didn’t specify or forbid 2 specifically.
replies(2): >>43579142 #>>43580237 #
2. FeepingCreature ◴[04 Apr 25 07:02 UTC] No.43579142[source]▶
I would argue this is just fitting.
replies(1): >>43584348 #
3. IanCal ◴[04 Apr 25 10:17 UTC] No.43580237[source]▶
> If you show the model values for y, but they are 2 in 99% of all cases, it’s likely going to yield 2 when asked about the value of y

That's not overfitting. That's either just correct or underfitting (if we say it's never returning anything but 2)!

Overfitting is where the model matches the training data too closely and has inferred a complex relationship using too many variables where there is really just noise.

4. fluidcruft ◴[04 Apr 25 16:01 UTC] No.43584348[source]▶
If you take the perspective of all the possible responses to the request, then it is overfit because it only returns a non-generalized response.

But if you look at it from the perspective that there is only one example to learn, from it is maybe not over it.