alt Hacker NewsSomething I've found surprisingly effective is telling ChatGPT to "use credible sources" - you can then watch its thinking trace and see it do things like ruling out random blogs, considering media publications with a good reputation for fact checking, and double-checking information that seems unlikely.
Replies
westoque • today at 2:26 PM
I don't think random blogs should be ruled out. Just because a blog is random doesn't mean its untrue.
➕ show 2 replies
skorniienko • today at 2:19 PM
Love it, I'll run tests for "credible sources" and will compare the results. Could be a first feature-request implemented!
skorniienko • today at 4:20 PM
Added this as issue so I don't forget https://github.com/SerhiiKorniienko/bullshit-detector/issues...
For any LLM with web tool usage I’ll often suggest that it pull relevant papers from arXiv, with an expectation that it cite sources. I find that this helps improve accuracy and lets me go deeper into the material if I want to.