News for hackers. Stuff that matters.
Re:GPT-4 by billythemaniam on Tuesday March 14, 2023 @05:28PM (#35159046)
If you had full source code that fit into the context, do you think it could reliably answer questions about the code, build unit tests, generate documentation? I ask because that is the software equivalent of what you just described.
Re:GPT-4 by raincole on Tuesday March 14, 2023 @05:36PM (#35159172)
All we can do is guessing now until more people get access to the new API. My bet is it can at least generate documentation pretty well.
Re:GPT-4 by varenc on Tuesday March 14, 2023 @06:15PM (#35159787)
I think anyone that pays $20/month for ChatGPT plus has immediate access? At least I already have access now. I’m assuming new subscribers get access too.
Re:GPT-4 by raincole on Tuesday March 14, 2023 @06:58PM (#35160474)
As far as I can tell, ChatGPT plus is the 8096 tokens version. The 30k token version is only available via API. I might misread it tho, it's not super clear on their site.

Are you sure you are accessing the 30k token version via ChatGPT plus?

Re:GPT-4 by varenc on Tuesday March 14, 2023 @07:14PM (#35160787)
No, you're right. The ChatGPT-4 interface has the lower token limit!
Re:GPT-4 by WinstonSmith84 on Wednesday March 15, 2023 @04:47AM (#35165543)
Here is the release notes confirming this https://help.openai.com/en/articles/6825453-chatgpt-release-...

It was not clear however that there was this token limit restriction, thanks

Re:GPT-4 by ElijahLynn on Wednesday March 15, 2023 @01:19PM (#35171633)
I have the Plus plan and it just asked me if I wanted to try it. And currently it is limiting requests for ChatGPT-4 and displays this in the UI.

"GPT-4 currently has a cap of 100 messages every 4 hours"

Re:GPT-4 by hooande on Tuesday March 14, 2023 @06:49PM (#35160311)
Yes. It still can't attend meetings, collaborate on projects or set priorities. Or any of the other things programmers spend most of their time doing.

Also I'd guess that it still generally sucks at programming. Code has a lot of very similar sequences and logical patterns that can be broken, which makes it prone to hallucinating. I'd imagine that more parameters will help with this.