News for hackers. Stuff that matters.
Re:SafeGPT: New tool to detect LLMs' hallucinations, biases ... by jsheard on Friday April 21, 2023 @09:43AM (#35653625)
I can't help but notice your account only has two posts, with the other one also praising a giskard.ai submission. Anything you'd like to disclose?
Re:SafeGPT: New tool to detect LLMs' hallucinations, biases ... by hallucy on Friday April 21, 2023 @10:34AM (#35654368)
You should assume everything posted on the internet has an ulterior motive. Relying on disclosures simply allows actual bad actors to avoid scrutiny.

(And no one cares that you used to work at Microsoft or whatever).

Re:SafeGPT: New tool to detect LLMs' hallucinations, biases ... by cantaloa on Friday April 21, 2023 @11:12AM (#35654978)
Well said.