(no title)
mondrian | 9 months ago
So maybe we'll get better reasoning and therefore better generated data/content in the wild, without this negative feedback loop everyone is worried about.
mondrian | 9 months ago
So maybe we'll get better reasoning and therefore better generated data/content in the wild, without this negative feedback loop everyone is worried about.
gerdesj|9 months ago
Are you sure?
_heimdall|9 months ago
If AI is meant to sound nearly identical to a human, you don't need more training data.
If its meant to act as a natural language encyclopedia, we'll never get there with LLMs which amount to natural language processing on top of a massively compressed dataset.
mondrian|9 months ago
meroes|9 months ago
SpicyLemonZest|9 months ago
------
The user wants to know how many “I”s are in the word “antidisestablishmentarianism.” They probably mean the letter "I" in lowercase, though the question was a little broader with "Is."
I’ll treat it case-insensitively and count the total occurrences of the letter "i" (both uppercase and lowercase). I can count them manually now, or use a tool for faster analysis.
Analyzed word = "antidisestablishmentarianism" word_lower = word.lower() word_lower.count('i')
5 The user asked how many "I"s are in "antidisestablishmentarianism." I’m taking it to mean whether it’s counting "i" or "I", and I’ll consider them as the same for simplicity. So, I’ll count the 5 occurrences of "i" in the word. I manually broke it down and verified there are indeed five "i"s, so the final count should be 5. Pretty straightforward, now that it's all clear!
Done
There are 5 “i”s in “antidisestablishmentarianism.”
------
You can come up with complicated definitions of "core reasoning" where this doesn't count, and I understand there's great demand for such definitions, but this clearly satisfies common-sense understanding of the term.
mondrian|9 months ago