News for hackers. Stuff that matters.

A comment on SafeGPT: New tool to detect LLMs' hallucinations, biases and privacy issues. Parent comment

Re:SafeGPT: New tool to detect LLMs' hallucinations, biases ... by thfuran on Friday April 21, 2023 @09:58AM (#35653842)
One with only weights and no biases in the ANN is unbiased.
[ Parent | on HN ]
Re:SafeGPT: New tool to detect LLMs' hallucinations, biases ... by taneq on Friday April 21, 2023 @10:05AM (#35653956)
I feel like this went underappreciated. [b] = [0] indeed.
[ Parent | on HN ]
Re:SafeGPT: New tool to detect LLMs' hallucinations, biases ... by sebzim4500 on Friday April 21, 2023 @03:07PM (#35658518)
Someone I know thought that LLaMA was unbiased because they 'read' the paper and clearly didn't know what anything meant. A great example of "a little knowledge is a dangerous thing".
[ Parent | on HN ]