It still can’t count the Rs in strawberry, I’m not worried.
-
-
-
-
-
Note that my tests were via groq and the r1 70B distilled llama variant (the 2nd smartest version afaik)
-
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
-
I'm not seeing any reasoning, that was the point of my comment. That's why I said "supposed"
-
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.
-
And where did it happen to find all those pictures of cats?
-
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.
-
The "reasoning" models and the image generation models are not the same technology and shouldn't be compared against the same baseline.
-
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.
-
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!
-
Dawg you're unhinged
-
That’s a lot of processing just to count letters
feel free to ask Google/Bing/Your favourite search engine to do the same
-
Unrelated to the convo but for those who'd like a visual on how LLM's work: https://bbycroft.net/llm
-
Search engines are not designed to answer questions. Apples and oranges.
-
Downvoting wasn't enough. Disliking AI is not a good enough reason to be a jackass to everyone.
