GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text

Re:GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text by gmadsen on Sunday December 03, 2023 @09:45AM (#38507406)

its referring to the search space of valid segmentations, which if set up as a classical problem, it would be some type of DP with backtracking from deadend paths. The full input is known in both cases, its just that gpts arch doesn't need to search any segmentation space, its billions of parameters aproximate the function needed to arrive at the correct answser

[ Parent | on HN ]

Re:GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text by umanwizard on Sunday December 03, 2023 @11:00AM (#38508013)

You wouldn’t even be able to solve this in the standard leetcode DP problem way, because it’s ambiguous if all you know is which words are valid. For example THESEA could be either “THE SEA” or “THESE A”. You need to have a model of English grammar to realize that the former is much more likely to be part of a valid sentence than the latter.

[ Parent | on HN ]

Re:GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text by eutectic on Sunday December 03, 2023 @12:11PM (#38508627)

I think even a bigram model would provide enough information.

[ Parent | on HN ]

Re:GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text by Y_Y on Sunday December 03, 2023 @12:21PM (#38508741)

Is that "big-ram" or "bi-gram"?

[ Parent | on HN ]

Re:GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text by waveBidder on Sunday December 03, 2023 @01:26PM (#38509424)

it's big RAM now! (a bi-gram is the probability of a word given the previous 2.

[ Parent | on HN ]

Re:GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text by somebodythere on Sunday December 03, 2023 @01:24PM (#38509413)

Bi-gram aka pairs of words

[ Parent | on HN ]

Re:GPT-4 Can Almost Perfectly Handle Unnatural Scrambled Text by esafak on Sunday December 03, 2023 @02:16PM (#38509842)

I think it was a rhetorical question.

[ Parent | on HN ]