Hacker News Reader

Comment by dekhn | Hacker News Reader

I think the tweeter is being a bit too pedantic. Personally I spent some time thinking about embeddings, manifolds, the structure of language, scientific naming, and what the decoding of the points near the center of clusters in embedding spaces look like (archetypes), after seeing this paper. I think making networks and asking them to explain themselves using their own capabilities is a wonderful idea that will turn out to be a fruitful area of research in its own right.

View on HN

I concur that the tweeter is being pedantic.

This is largely some embedding of semantics that we currently do not fully have a mapping for, precisely because it was generated stochastically.

Saying it was "not true" seems like clickbait.

Especially since his results confirm most of what the original thread claimed. A couple of the inputs did not reliably replicate, but "for the most part, they're not true" seems straightforwardly false. He even seems to deliberately ignore this sometimes, such as when he says "I don't see any bugs" when there is very obviously a bug in the beak of all but two or three of the birds.

Lower in the same thread he accepts that his main tweet was clickbaity, and that actually there's consistency in some of the results.

Not really, he afterwards says that he was more trying to inject some humility. He really doesn't think this is measuring anything of interest. For the birds result in particular, see https://twitter.com/BarneyFlames/status/1531736708903051265.

If I read what that tweet says properly, the system ended up outputting things that were almost scientific nomenclature for the general class of items it was being asked to draw. There are probably many examples of "bird is an instance of class X" in the text but they are not consistent, and the resulting token vector is a point near the center of "birdspace".

Yes. Indeed, it seems to interpret a lot of nonsense tokens it doesn't recognize as though it's probably the Latin / scientific term for some sort of species it doesn't remember very well (keeping in mind that all these systems are attempting to compress a large corpus into a relatively small space). I think https://twitter.com/realmeatyhuman/status/153173904648934195... is best illustrative of this phenomenon.

So, it's certainly an "interesting" result in the sense that it shows how these kinds of systems work, but it's definitely not a language.

Why is it important if it's "a language" or not? What we're talking about are concept representations (nouns), not languages. But I think most people who read "DALL-E has a secret language" probably picked up on that because we're accustomed to the hype in machine learning naming things to sound like they are more profound and powerful than they really are.

It's important if it's a "language" because the original thread claimed that it was one (and indeed, a number of comments in responses to this article are still making that claim). You may argue that discovering how DALL-E tries to map nonsense words to nouns is independently interesting, and that's fine (I don't find it interesting personally though--considering it has to pick something, and the evidence that these spaces are not particularly robust when confronted with far out of sample input, I don't even think calling it a secret vocabulary would be accurate), but the authors should reasonably expect some pushback if they argue that this is linguistics.

It didn't pick "something"- it chose scientific nomenclature as a basis, and synthesized new classes from that basis.

They're not nonsense words, they're words with high probability which are not seen in the dataset.

When questioned about the change of tone, he answers "Well... a little bit of twitter hype makes a thread go a long way".

https://twitter.com/emnode/status/1531852124501553153

When I zoomed in, I felt only four in ten birds clearly had anything in their beaks, and in each case it looked like vegetable matter. In the original set, only one clearly has an insect in its beak.

Are there higher-resolution images to be had?

If DALL-E had a choice to output "Command not understood", maybe we wouldn't be discussing this.

Like those AIs that guess what you draw, and recognize random doodling as "clouds", DALL-E is probably using the least unlikely route. That a gibberish word is drawn as a bird is maybe because it was "bird (2%), goat (1%), radish (1%)".

1. https://quickdraw.withgoogle.com

This is a good point. The fact that DALL-E will try to render something, no matter how meaningless the input, is a trait it has in common with many neural networks. If you want to use them for actual work, they should be able to fail rather than freestyle.

That's extremely optimisic. When faced with gibberish, the "confidences" are routinely 90%+ as with "meaningful" input.

It's almost as-if its an illusion designed to fool, we, the users.. by only providing inputs meaningful to us, we come to the foolish idea that it understands these inputs.

> asking [neural networks] to explain themselves using their own capabilities

Exactly. This could be profound. I'm looking forward to further work here. Sure, the examples here are daft, but developing this approach could be like understanding a talking lion [0] only this time it's a lion of our making.

[0] https://tzal.org/understanding-the-lion-the-in-joke-of-psych...

I think it’s more likely we can train two neural networks, one to make the decision and one to take the same inputs (or the same inputs plus the output from the first one) and generate plausible language to explain the first. This seems to correspond to what we dimwits consciousness and frankly I would doubt one system can accurately explain its own mechanism. People surely can’t.

It’s a fruitful area of research for sure, but there is a huge gap between “it invented pig Latin” and “it invented Esperanto/Lojban”. Referring to the first as inventing a language is very misleading.

Reply on news.ycombinator.com