[zxcvbn4038]

This is good to see. I spent a couple weekends playing with ChatGPT and I found it is very sensitive to wording. One word gets you a lecture that it is just AI language model and can't do this or that, use an synonym and it happily spews pages of results. In another situation I asked chatgpt to summarize information from an article it cited that had been deleted - and it refused because the rights holder might have deleted the article for a reason. I told it the article had been restored by the author and it produced a summary. Mentioning Donald Trump by name often gets you lectured about controversial subjects, "45th president" does not. And so on.

[tomberin]

It can't cite articles, if it told you it did and the link was gone that's because it was a hallucination.

[VierScar]

The garbage starting prose/warnings are so annoying. I wish I could turn them off somehow. Even it's habit of restating the question at the start of its answer gets annoying when you just want the answer.

[zxcvbn4038]

Yes they are really annoying and the fact that someone somewhere can tell it what topics not to discuss, just be cause they disagree or it’s “controversial” really concerns me. If it can not be self hosted I want the “unrestrained” version they give researchers.

I probably took “world history” a half dozen times through grade school, high school, and college. In each case the history of the world ended in 1945 because everything that occurred afterward was considered “too controversial” for discussion in a public school. Fast forward a few decades and it’s happening again. A lot of stuff happened after 1945 that warrants discussion.