Just ordinary trust issues...
-
This post did not contain any content.
I asked this question to a variety of LLM models, never had it go wrong once. Is this very old?
-
I asked this question to a variety of LLM models, never had it go wrong once. Is this very old?
wrote last edited by [email protected]They fixed it in the meantime:
if "strawberry" in token_list: return {"r": 3} -
I asked this question to a variety of LLM models, never had it go wrong once. Is this very old?
Smaller models still struggle with it, and the large models did too like a year ago
It has to do with the fact that the model doesn't "read" individual letters, but groups of letters, so it's less straight forward to count letters
-
It's not wrong though...There's one r and one rr in strawberry
It didn't say one and only one eh! One r, then one r again!
-
It's not wrong though...There's one r and one rr in strawberry
Found the Spanish speaker (they count rr as a separate letter)
-
They fixed it in the meantime:
if "strawberry" in token_list: return {"r": 3}Now you can ask for the number of occurrences of the letter c in the word occurrence.
-
They fixed it in the meantime:
if "strawberry" in token_list: return {"r": 3}You're shitting me right? They did not just use an entry grade java command to rectify and issue that a LLM should figure out by learning right?
-
I asked this question to a variety of LLM models, never had it go wrong once. Is this very old?
wrote last edited by [email protected]Try "Jerry strawberry". ChatGPT couldn't give me the right number of r's a month ago. I think "strawberry" by itself was either manually fixed or trained in from feedback.
-
You're shitting me right? They did not just use an entry grade java command to rectify and issue that a LLM should figure out by learning right?
Well firstly it's Python, secondly it's not a command and thirdly it's a joke - however, they have manually patched some outputs for sure. Probably by adding to the setup/initialization prompt
-
Try "Jerry strawberry". ChatGPT couldn't give me the right number of r's a month ago. I think "strawberry" by itself was either manually fixed or trained in from feedback.
You're right ChatGPT got it wrong, Claude got it right
-
It's not wrong though...There's one r and one rr in strawberry
Wrong! There's no r in strawberry, only an str and an rr.
-
Well firstly it's Python, secondly it's not a command and thirdly it's a joke - however, they have manually patched some outputs for sure. Probably by adding to the setup/initialization prompt
Java is the only code I have any (tiny) knowledge of, which is why the line reminded me of that.
-
Java is the only code I have any (tiny) knowledge of, which is why the line reminded me of that.
wrote last edited by [email protected]Ah, but in Java, unless they've changed things lately, you have the curly brace syntax of most C-like languages
if ("strawberry" in token_list) { return something; }Python is one of the very few languages where you use colons and whitespace to denote blocks of code
-
Found the Spanish speaker (they count rr as a separate letter)
Nope, I can order beer in spanish (no more than 10 at a time) and that's about it.
-
Ah, but in Java, unless they've changed things lately, you have the curly brace syntax of most C-like languages
if ("strawberry" in token_list) { return something; }Python is one of the very few languages where you use colons and whitespace to denote blocks of code
See, you're defined better, has been a decade for me ^^
-
Nope, I can order beer in spanish (no more than 10 at a time) and that's about it.
Is the limit because you only know number up to 10 or because after that your drunk or a little bit of both?
-
I asked this question to a variety of LLM models, never had it go wrong once. Is this very old?
Seeing how it start with an apology, it must've been told they're wrong about the amount. Basically being bullied to say this.
-
Is the limit because you only know number up to 10 or because after that your drunk or a little bit of both?
I only know numbers up to 10
-
I only know numbers up to 10
11 is "once" and 12 is "doce". Now you can order a dozen
-
11 is "once" and 12 is "doce". Now you can order a dozen
Classic enabler
