this post was submitted on 01 Dec 2024

48 points (88.7% liked)

Futurology

1984 readers

131 users here now

founded 2 years ago

MODERATORS

AwesomeLowlander

48

Multiple LLMs voting together on content validation catch each other’s mistakes to achieve 95.6% accuracy. (arxiv.org)

submitted 2 months ago by Lugh to c/futurology

27 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[–] pennomi@lemmy.world 3 points 2 months ago

It depends. A lot of LLMs are memory-constrained. If you’re constantly thrashing the GPU memory it can be both slower and less efficient.