News for hackers. Stuff that matters.
Re:Latest ChatGPT 4 System prompt (1,700 tokens) by sweetheart on Wednesday February 07, 2024 @02:33PM (#39293131)
> secretly pre-adjust outcomes without disclosure.

Isn't that the whole training process though. Unless you know of every piece of data used to train it, and how each of those data was prepared, you have to assume that any LLM you use is coming with a particular viewpoint baked in.

There are no comments on this comment yet.