It still can’t count the Rs in strawberry, I’m not worried.

[email protected]

That isn't at all how something like a diffusion based model works actually.

[email protected]

So what training data does it use?

They found data to train it that isn't just the open internet?

[email protected]

The "reasoning" you are seeing is it finding human conversations online, and summerizing them

[email protected]

Regardless of training data, it isn't matching to anything it's found and squigglying shit up or whatever was implied. Diffusion models are trained to iteratively convert noise into an image based on text and the current iteration's features. This is why they take multiple runs and also they do that thing where the image generation sort of transforms over multiple steps from a decreasingly undifferentiated soup of shape and color. My point was that they aren't doing some search across the web, either externally or via internal storage of scraped training data, to "match" your prompt to something. They are iterating from a start of static noise through multiple passes to a "finished" image, where each pass's transformation of the image components is a complex and dynamic probabilistic function built from, but not directly mapping to in any way we'd consider it, the training data.

[email protected]

Oh ok so training data doesn't matter?

Or only when it makes your agument invalid?

Tell me how you moving the bar proves that AI is more intelligent than the sum of its parts?

[email protected]

https://ibb.co/wVNsn5H

https://ibb.co/HpK5G5Pp

https://ibb.co/sp1wGMFb

https://ibb.co/4wyKhkRH

https://ibb.co/WpBTZPRm

https://ibb.co/0yP73j6G

Note that my tests were via groq and the r1 70B distilled llama variant (the 2nd smartest version afaik)

[email protected]

It’s because LLMs don’t work with letters. They work with tokens that are converted to vectors.

They literally don’t see the word “strawberry” in order to count the letters.

Splitting the letter probably separates them into individual tokens

[email protected]

I'm not seeing any reasoning, that was the point of my comment. That's why I said "supposed"

[email protected]

It doesn't search the internet for cats, it is pre-trained on a large set of labelled images and learns how to predict images from labels. The fact that there are lots of cats (most of which have tails) and not many examples of things "with no tail" is pretty much why it doesn't work, though.

[email protected]

And where did it happen to find all those pictures of cats?

[email protected]

It's not the "where" specifically I'm correcting, it's the "when." The model is trained, then the query is run against the trained model. The query doesn't involve any kind of internet search.

[email protected]

The "reasoning" models and the image generation models are not the same technology and shouldn't be compared against the same baseline.

[email protected]

And I care about "how" it works and "what" data it uses because I don't have to walk on eggshells to preserve the sanctity of an autocomplete software

You need to curb your pathetic ego and really think hard about how feeding the open internet to an ML program with a LLM slapped onto it is actually any more useful than the sum of its parts.

[email protected]

Ah, you seem to be engaging in bad faith. Oh, well, hopefully those reading at least now between understanding what these models are doing and can engage in more informed and coherent discussion on the subject. Good luck or whatever to you!

[email protected]

Dawg you're unhinged

[email protected]

That’s a lot of processing just to count letters

feel free to ask Google/Bing/Your favourite search engine to do the same

[email protected]

Unrelated to the convo but for those who'd like a visual on how LLM's work: https://bbycroft.net/llm

[email protected]

Search engines are not designed to answer questions. Apples and oranges.

[email protected]

Downvoting wasn't enough. Disliking AI is not a good enough reason to be a jackass to everyone.

agnos.is Forums

It still can’t count the Rs in strawberry, I’m not worried.