News for hackers. Stuff that matters.
Re:Amazon's new Alexa delayed – again – over incorrect answers by WheelsAtLarge on Friday February 14, 2025 @06:30PM (#43054219)
Large language models (LLMs) do not have a mechanism to prevent them from giving incorrect answers. While I believe they are still useful, they will never be 100% accurate. We need to recognize that users will frequently receive wrong answers. To improve reliability, there should be a system in place that involves humans in the process of verifying the accuracy of the responses.
Re:Amazon's new Alexa delayed – again – over incorrect answers by bttrpll on Saturday February 15, 2025 @10:58PM (#43065182)
Humans get things wrong too. Humans are not 100% accurate; not by any stretch.
Re:Amazon's new Alexa delayed – again – over incorrect answers by bookofjoe on Friday February 14, 2025 @06:23PM (#43054168)