Re:SafeGPT: New tool to detect LLMs' hallucinations, biases ...
by danShumway on Friday April 21, 2023 @12:55PM
(#35656621)
> Currently, fact checking works on straight facts. It does a Google Search and uses LLMs to shorten it.
So your fact-checking LLM is also vulnerable to injection and unethical prompting then when it ingests website text. And a Google search is far, far away from fact checking, particularly for the subtle errors that GPT-4 is prone to making.
So your fact-checking LLM is also vulnerable to injection and unethical prompting then when it ingests website text. And a Google search is far, far away from fact checking, particularly for the subtle errors that GPT-4 is prone to making.