Live data from Hacker News

DALL-E 2 has a secret language

twitter.com

31–40 of 118 posts

Re: DALL-E 2 has a secret language

#31
My first thought upon reading this: what if DALL-E (or a similar AI) uncovers some kind of hidden universal language that is somehow more "optimal" than any existing language?

i.e. anything can be completely described in a more succinct manner than any current spoken language.

Or maybe some kind of universal language that naturally occurs and any semi-intelligence life can understand it.

Fun stuff!

Re: DALL-E 2 has a secret language

#34
Shouldn't this be expected to a certain extent?

Gibberish has to map _somewhere_ in the models concept space.

Whether is maps onto anything we'd recognise as consistent doesn't mean that the AI wouldn't have some concept of where it relates, as other people have noted, the gibberish breaks down when you move it into another context, but who's to say that Dall-E 2 isn't remaining consistent to some concept it understands that isn't immediately recognisable to us.

The interesting part is if you can trick it to spit out gibberish in targeted areas of that concept space using crafted queries.

Re: DALL-E 2 has a secret language

#35
post #7

Possibly related: In 2017 AI bots formed a derived shorthand that allowed them to communicate faster: https://www.facebook.com/dhruv.batra.dbatra/posts/1943791229... > While the idea of AI agents inventing their own language may sound alarming/unexpected to people outside the field, it is a well-established sub-field of AI, with publications dating back decades. > Simply put, agents in environments attempting to solv…

Which, to a lessor extent, isn't too terribly different from humans if you think about. We don't use a full new language but every profession has it's own jargon. Some of it spans the whole industry and some is company-specific.

Re: DALL-E 2 has a secret language

#36
post #16

One of the replies is a thread with a fairly convincing rebuttal, with examples: https://twitter.com/Thomas_Woodside/status/15317102510150819...

I'm not sure it's a convincing rebuttal, the examples shown all seem to have some visible commonality.

Eg. "Apoploe vesrreaitais" Could refer to something along the lines of a "fan / wedge" or "wing-like"

If you look at the examples of cheese, when compared to the "birds and cheese" the cheese tends to be laid out in a fan like pattern and shaped in sharp angled wedges.

Re: DALL-E 2 has a secret language

#38
post #34

Shouldn't this be expected to a certain extent? Gibberish has to map _somewhere_ in the models concept space. Whether is maps onto anything we'd recognise as consistent doesn't mean that the AI wouldn't have some concept of where it relates, as other people have noted, the gibberish breaks down when you move it into another context, but who's to say that Dall-E 2 isn't remaining consistent to some concept it understa…

You could expect that gibberish is distributed uniformly in latent space, disconnected from it's langual counterpart -- after all those are textual inputs that model have never seen, and it can't even map words it have seen many times to their writing in image properly: "seafood" word and "seafood" image are in the same place in latent space, but "seafood" word in image isn't. Yet some gibberish word in image is, and also the same gibberish word is. It's very counterintuitive for me.

Re: DALL-E 2 has a secret language

#39

My first thought upon reading this: what if DALL-E (or a similar AI) uncovers some kind of hidden universal language that is somehow more "optimal" than any existing language? i.e. anything can be completely described in a more succinct manner than any current spoken language. Or maybe some kind of universal language that naturally occurs and any semi-intelligence life can understand it. Fun stuff!

I think something like this is actually quite likely.

I’ve been wondering if there is a way to do psychological experiments on these large language models that we couldn’t do with a person.

Re: DALL-E 2 has a secret language

#40
post #36
post #16

One of the replies is a thread with a fairly convincing rebuttal, with examples: https://twitter.com/Thomas_Woodside/status/15317102510150819...

I'm not sure it's a convincing rebuttal, the examples shown all seem to have some visible commonality. Eg. "Apoploe vesrreaitais" Could refer to something along the lines of a "fan / wedge" or "wing-like" If you look at the examples of cheese, when compared to the "birds and cheese" the cheese tends to be laid out in a fan like pattern and shaped in sharp angled wedges.

I'm curious what it generates when given randomly generated strings of seemingly pronounceable words like "Fedlope Dipeioreitcus".
Post reply on HN