OpenAI’s policies hinder reproducible research on language models

Re:OpenAI’s policies hinder reproducible research on languag... by allemagne on Thursday March 23, 2023 @11:34AM (#35276405)

One task that ChatGPT-3.5 is hilariously bad at is reversing strings (both words and pseudorandom input). It seems to have only a vague concept of what that means, even if I try to hold its hand through the process. Maybe some prompt engineering can get it to succeed on anything longer than four letters.

ChatGPT-4 meanwhile seems to have no issue with this at all.

[ Parent | on HN ]

Re:OpenAI’s policies hinder reproducible research on languag... by zarzavat on Thursday March 23, 2023 @05:44PM (#35281713)

Have you tried inserting spaces between the characters? This may just be a tokenization issue, rather than anything due to the model per se.

Reversing a string is somewhat of a pathological case for language models, because they see tokens not characters. Learning that the token “got” and token “tog” are mirror images is only useful for string reversal and generating palindromes. Unless they are trained specifically for this task, they may not be able to do it. They should however be able to see that “g o t” and “t o g” are mirror images.

Infamously, early versions of GPT-3 tokenized numbers as grouped tokens, nerfing its calculation abilities, because it would tokenize a number such as 12345 as (illustratively) 12 34 5 which is obviously a harmful representation.

[ Parent | on HN ]