[ducktective]

I asked GPT-4 for the Imagemagick command to make the white parts of an image, semi-transparent.

It generated a command that made the fuzzy white parts [+1 on fuzzy] fully transparent [bad].

I told it that the result is not semi-transparent.

It apologized and gave me another command that produced a blank image. In another case a grayish image.

I told it this is not what I wanted, and it just looped here saying I'm sorry and giving me one of these above solutions.

As a matter of fact, this looping back and forth between half-working and non-working solutions is something that I've experienced every time when the first result was not what I asked...

Aside from the possibility of "emerging intelligence", I don't think this is the way to the AGI.

[p1necone]

> Aside from the possibility of "emerging intelligence", I don't think this is the way to the AGI.

My intuition is that this is the only way to create AGI. I don't think anyone is ever going to carefully intentionally construct an AGI, it's almost certainly going to emerge from something conceptually fairly simple.

I don't think it's impossible that our own brains are also basically just a big statistical prediction model too. Maybe AGI just requires our models to be 10/100/1000x as good. Or our training data needs to be broader in a qualitative way rather than a quantitative way that we haven't quite worked out yet.

[ducktective]

Can you prove Fermat last theorem via giving a high parameter LLM a very large amount of mathematical knowledge?

[317070]

Yes.

I would even be surprised if in 10 years an AI wouldn't be able to decide on the Riemann hypothesis given enough compute.

The rate of progress made in the last 10 years has been enormous, but blanks in comparison to the acceleration of the last year. Unless there are yet unknown limits to our current methods, there does not seem anything to stop us from building machines that outperform the field of human mathematics.

I could sketch you a couple of paths there if we manage to leverage current LLM to become self-improving. But even if we don't manage to do that, there are paths to leverage LLM's to solve mathematics. I can outline truly remarkable approaches, which this comment is too small to contain.

[texuf]

Imagine you’ve only been a programmer for 2 years. Imagine not knowing what imagemagick is. Now get an answer that gets you 99% of the way to where you want to be. Now look at the documentation to see why the parameters aren’t doing what you want them to do. You just saved hours of work.

[ducktective]

Yes, GPT and LLMs got to be the most significant leap in the field of AI from 2010s onwards...It kinda "solves" NLP. It is the best human-language-based UI that humanity has every created.

But the point is, this thing does not understand what it's doing...it's become a cliche but the people who coined the term "statistical parrot" really knew what's up.

Like, I think there could be some GOFAI technique that may solve "figuring out how to use a tool like imagemagick/ffmpeg" mathematically, formally and deterministically.

And again, I'm all basing my view on the fact that this "emerging intelligence" is a mirage.

[simonw]

What did you conclude from this?

Was your conclusion "GPT-4 isn't any good for imagemagick commands" or "GPT-4 isn't useful for anything"?

[ducktective]

GPT-4 isn't good for tasks it was not trained on.

[ilaksh]

Did you try pasting in the relevant reference sections for those ImageMagick commands/options?

[ducktective]

No, I didn't know exactly what commands were useful. And I'm not subscribed to the pro version so pasting the whole documentation would cost a lot.