|
|
|
|
|
|
by gamegoblin
546 days ago
|
|
|
Author of the tweet here. A few notes: 1. No cherry picking 2. This was the original ChatGPT, i.e. the GPT3.5 model, pre-GPT4, pre-turbo, etc 3. This capability was present as early as GPT3, just the base model —- you'd prompt it like "<python program> Program Output:" and it would predict the output |
|
|