3 ms·
Me: Count backwards from ten GPT-4: 10, 9, 8, 7, 6, 5, 4, 3, 2, 1 Me: Count backwards from a million to 999990 GPT-4: 1,000,000, 999,999, 999,998, 999,997, 9
by stavros 3y ago
Me: Count backwards from ten
GPT-4: 10, 9, 8, 7, 6, 5, 4, 3, 2, 1
Me: Count backwards from a million to 999990
GPT-4: 1,000,000, 999,999, 999,998, 999,997, 999,996, 999,995, 999,994, 999,993, 999,992, 999,991, 999,990
I don't know about that.
- 15457345234 3y agoI don't know how that connects in any way to what I and the commenter preceding me wrote.
- stavros 3y agoYou said that sentences aren't formed by probability from an existing corpus, as that method can't count backwards. GPT-4, a system based on such a method, can count backwards, thus disproving your claim.
- woodruffw 3y agoI’m pretty sure the person you’re responding to is saying that counting is a formal operation with a formal definition, and that when GPT “counts” it isn’t doing that formal operation. The fact that it can semi-reliably emit ordered sequences isn’t counterevidence, for the same reason that memorizing the order of 0 to 100 isn’t evidence of an understanding of the inductive structure of counting.
- jacquesm 3y agoHow long a sequence of numbers (or how many sequences of different kinds of numbers) would it take to convince someone that it does do a formal operation? Kids don't do a 'formal operation' when they count from 1 to 10, they just recite a list they've memorized. If they can do it from 1 to 1,000,000 you can be fairly sure it is no longer a memorized list.
- 15457345234 3y ago> thus disproving your claim Is there an alternative conclusion which you could reach here?