News for hackers. Stuff that matters.
Re:How OpenElections Uses LLMs by timschmidt on Thursday June 19, 2025 @10:13PM (#44324157)
I've seen similar. I wonder if traditional organizational solutions, like those employed by the US Military or IBM, might be applicable. Redundancy is one of their tools for achieving reliability from unreliable parts. Instead of asking a single LLM to perform the task, ask 10 different LLMs to perform the same task 10 different times and count them like votes.
Re:How OpenElections Uses LLMs by latentpot on Thursday June 19, 2025 @10:42PM (#44324271)
Why complicate? One LLM works, another reflects and then a decision engine to review would be cheaper.
Re:How OpenElections Uses LLMs by Normal_gaussian on Sunday June 22, 2025 @06:12AM (#44345597)
Yeah, what I did to "solve" my issue was to use several models (4), then where there was any disagreement farm out to humans (2). 60% went to humans in the end.

I suspect if I'd done some corrective transformations before LLM scanning the success rate would have been higher, but the cost threshold of the project didn't warrant it.