It cannot read. It doesn’t see words or letters. It works with Tokens which words are converted into. It cant count the number of letters in a word because it can’t see them. OpenAI has a Tokenizer you can plug a prompt into to see how its broken up, but youre asking a fish to fly.
And a single “S” is also a token. Which has vectors to all other words that start with an S.
One thing to point out here is that the word sentences is severely mistyped as “sententences”. That’s not going to help.
I asked it how many “n” mayonnaise has and it came up with manaonnanaise
I feel like if these things ever become really self aware, they will be super fucking with us
Idk what I’m doing wrong, thankfully it always seems to listen and work fine for me lmao
Ask it to list the n’s
Look at the first question in the my first screenshot. It gets that question correct for “mayonnaise” lol
It got it wrong when I asked it to list them
I feel like ChatGPT itself probably has a fairly loose temp setting (just a hunch) and I tend to set my conversations up to be more on the strict side
I imagine that’s why our results differ, it’s strange OpenAI doesn’t let ChatGPT site users or at least premium users adjust anything really yet.
Always has been 🔫
It has not. ChatGPT has been a monumental achievement and has been capable of performing previously impossible and highly impressive tasks. This is new behavior for it.
Y’all seem to gloss over the word artificial when it comes to reading “artificial intelligence”. That or you’re leaning too hard on the first definition…
- made or produced by human beings rather than occurring naturally, especially as a copy of something natural. “her skin glowed in the artificial light”
- (of a person or their behavior) insincere or affected. “an artificial smile” 🤖
To be fair that feature sucked since the very beginning, at least for me.
