Re:The DeSantis Campaign Texted Me with a Large Language Model
by retrocryptid on Wednesday August 16, 2023 @03:14PM
(#37152159)
Or candidates could just publish a paper describing their positions on issues and policy objectives.
[ Parent
| on HN ]
Re:The DeSantis Campaign Texted Me with a Large Language Model
by function_seven on Wednesday August 16, 2023 @03:17PM
(#37152202)
But that makes it too easy to lie, omit, and equivocate. If the LLM is trained on all of their public statements over the last X years, and any official documents authored by them, then—theoretically!—you get something that's harder to manipulate.
Re:The DeSantis Campaign Texted Me with a Large Language Model
by retrocryptid on Wednesday August 16, 2023 @03:30PM
(#37152388)
Aha. I was thinking you were suggesting it be trained by the campaign. I'm usually bearish about how LLMs are being used, but if you created a corpus of legit sourced documents that humans could peruse, and added a feature to the LLM that allowed it to cite which document(s) it used to answer a question, that would be quite interesting.
Re:The DeSantis Campaign Texted Me with a Large Language Model
by commondream on Wednesday August 16, 2023 @03:22PM
(#37152272)
"As a supporter of Ron DeSantis I can neither confirm or deny if I am more accurate than an official policy document."
Re:The DeSantis Campaign Texted Me with a Large Language Model
by mrguyorama on Wednesday August 16, 2023 @04:11PM
(#37153025)
Why do you think an LLM, which has no connection to the actual candidate, would be able to give you useful information about said candidate?