I think you’re looking at this the wrong way.
This is similar to when text-embedding-ada-002 replaced 5 separate models because it performed as well, or better. I also use lesser models such as Ada for my own work. I would be blown away if they decided to completely remove them without some sort of way to transfer our training.
It’s best to follow what openai.com is compelled to do with whatever its investment partner, Microsoft does regarding your post.
Microsoft —>github news—>co-pilot—>Codex.
Personally I’m appalled at the entire monopoly and am looking at NVidea.
I’ve been using GPT-4 for coding since Friday, and I think I may revisit Codex.
GPT-4 is like a “Coder Buddy,” but you DO need to know what you’re doing.
It tried to get me to drop EVAL statements in my code last night until I pointed out security heh
That said, GPT-4 has been a super useful tool for me. You just have to know what information to give it and how to ask questions. It’s really sped up my dev time, and I’m not a real coder.
All that said, I’m thinking of firing up Codex again because I’ve been hearing good things. I don’t code a lot, but when I do, I like to get in the zone and get it done. GPT-4 has helped immensely with that.
ETA… and I just read more of the thread and realized Codex is going away? haha…
funny, I just hit the exact same roadblock last night. Tried to get it to write some code and it just refused. Even after I said it was just a local tool and there were no security issues.
Some HAL9000 sh*t…
Sam Altman tweeted an hour or so ago, that based on feedback, they have decided to keep supporting the Codex endpoint for “researchers”.
There is no indication what “researchers” means at this time.
Sorry, but I don’t understand the FUD in this thread.
For those who are interested in transitioning from Codex to GPT 3.5, it did not take me very much effort to recreate my simple code completion attempts, as indicated in this thread.
Did Open AI shut down Codex on a short notice? Yes. Could they have done a better job on the transition docs before notifying users? IMO yes. Does the change justify bitter FUD posting in this forum? IMO no.
Now we know, github copilot is going with chat as well 
Apparently as of this morning, plug has been pulled. 