-
I would comment that LLM are not a large math model (LMM) [which needs to be built - data set much smaller than language, or better large engineer model (LEM) would be more ideal]
-
So we need to help gpt4o along in how to solve the problem with a more concise prompt.
-
i used: Spell out the word strawberry letter by letter and each time you get the letter r increment an internal counter by 1. Show me the count as you check each letter
result:
As I spelled out the word “strawberry” letter by letter and incremented the counter for each “r,” here’s the process:
- s: Current Count of ‘r’: 0
- t: Current Count of ‘r’: 0
- r: Current Count of ‘r’: 1
- a: Current Count of ‘r’: 1
- w: Current Count of ‘r’: 1
- b: Current Count of ‘r’: 1
- e: Current Count of ‘r’: 1
- r: Current Count of ‘r’: 2
- r: Current Count of ‘r’: 3
- y: Current Count of ‘r’: 3
The final count is 3, which is incorrect based on the expected number of "r"s in “strawberry.” It seems that my earlier method provided the correct result of 2 "r"s. I’ll review the process to determine what might have gone wrong with the manual counting.
- and have it check results:
- Ok check results again and tell me if the result of 3 is correct or not
et’s review the results:
The word “strawberry” should be spelled out as follows:
- s
- t
- r (1st “r”)
- a
- w
- b
- e
- r (2nd “r”)
- r (3rd “r”)
- y
There are indeed 3 occurrences of the letter “r” in the word “strawberry.”
So, the result of 3 is correct. My earlier assessment that the word had only 2 "r"s was a mistake. The correct count is indeed 3 "r"s in “strawberry.”
*** and I had gpt4o explaining reason for mistake…
So do you have bad training where you data you trained on somehow makes you think there are only 2 r in the word strawberry?
ChatGPT said:
ChatGPT
The initial mistake I made wasn’t due to training data but rather a human-like error in my response. I incorrectly recalled or assumed the number of "r"s in “strawberry” without double-checking by counting the letters myself. This kind of error can happen in natural language processing models when handling simpler tasks, especially when responses are generated based on typical human assumptions.
Upon reviewing and correctly counting the letters using a systematic approach, it was clear that “strawberry” does indeed have 3 "r"s.
This highlights the importance of verifying simple details even when they seem obvious, as small errors can slip through, just as they might for a human. Thanks for your patience in walking through the correction process!
then testing method on different words
count number of s and i and p in the word Mississippi - use a method that will result in correct answer as done previously with strawberry.
ChatGPT said:
ChatGPT
The counts for the word “Mississippi” are as follows:
- s: 4 occurrences
- i: 4 occurrences
- p: 2 occurrences
This method provides the correct count for each letter.
4o
You said:
and now similar for hehudhhuyyuyyyyeyeyyyyuuue count each letter with optimal method to get correct answer. show your work line by line
ChatGPT said:
ChatGPT
Here are the counts for each letter in the string “hehudhhuyyuyyyyeyeyyyyuuue”:
- h: 4 occurrences
- e: 4 occurrences
- u: 6 occurrences
- d: 1 occurrence
- y: 11 occurrences
Each letter was counted using a loop that iterated through the string, incrementing the count for each specific letter as it was encountered. This method ensures the correct count for each letter.
It would be nice - if gpt4o could learn optimal methods for doing different tasks (and we could store those optimal methods that worked…or better yet it could learn those methods) we can then focus on more important problems to solve - and store those optimal methods of solving them…with of course the ability to prompt it (and verify) to use different solving methods if desired.
I want my AI engineer assistant - when?!