The results showed that out of the 512 questions, 259 (52%) of ChatGPT’s answers were incorrect and only 248 (48%) were correct. Moreover, a whopping 77% of the answers were verbose. […]
According to the study, the well-articulated responses ChatGPT outputs caused the users to overlook incorrect information in the answers.
“Users overlook incorrect information in ChatGPT answers (39.34% of the time) due to the comprehensive, well-articulated, and humanoid insights in ChatGPT answers,” the authors wrote.
The generation of plausible-sounding answers that are incorrect is a significant issue across all chatbots because it enables the spread of misinformation. In addition to that risk, the low accuracy scores should be enough to make you reconsider using ChatGPT for these types of prompts. —ZDNet
Post was last modified on 10 Aug 2023 2:43 pm
My virtual army of grey capsules is just barely smart enough to follow my avatar…
Oops. I’m going to bed now. I’ll fix it tomorrow.
First steps towards reconstructing a 30-year-old simulation. Marking the locations of the traditional performance stations…
Thank you, 1993 Dennis, for documenting this low-resolution (the background image was 640x480 pixels with…
Support the arts in your community! #augustwilson #radiogolf
I came of age playing too many CD-ROM point-and-click adventure games to ignore these steep…