I shouldn’t have to say this, but don’t use ChatGPT for technical advice.
In an experiment, I asked 40 questions about PostgreSQL. 23 came back with misleading or simply inaccurate information. Of those, 9 came back with answers that would have caused (at best) performance issues. One of the answers could result in a corrupted database (deleting WAL files to recover disk space).
LLMs are not a replacement for expertise.
Comments
RobotAlly · 9 May 2023
better have been using gpt4, or this experiment is totally invalid already. Much less in a few months when they release 4.5 or api access such that you can use it with a vector db...k · 9 May 2023
was it gpt4?Xof · 10 May 2023
What is it about GPT4 or 4.5 that would make it better in answering this kind of question?Xof · 10 May 2023
See my reply to RobotAlly's comment.