Or not.
I tried using ChatGPT for a coding session like ye days of old.
ChatGPT initially looks more competent at coding when before it was complete abandonment of all possibilities, now initially doing a better job of a GPTs “write metacode first” CoT, but…
The same behavior has hit ChatGPT’s GPT-4 as hit GPT-3.5-turbo around September (so that GPT-3.5 couldn’t code as well as crippled GPT-4?):
Hung up on past inputs.
Repeating the same code back to you with errors it just fixed re-included. Repeatedly. Rewriting the parameters and values of API functions to hallucinations. Rewriting the whole code base with a different encoder library and discarding 50% of the functionality, even against direct instructions not to alter more than instructed the second or third try.
A return to API gpt-4-0314 becomes a breath of fresh air, of an AI that works.