News for hackers. Stuff that matters.
Re:Alpaca RLHF-ed to beat ChatGPT by anothernewdude on Tuesday May 23, 2023 @09:23PM (#36052897)
I wonder how long "Using humans to rate the quality of other humans" thing can last. Surely academia has only so long before it collapses.
Re:Alpaca RLHF-ed to beat ChatGPT by plagiarist on Tuesday May 23, 2023 @09:36PM (#36052990)
You're asserting that current LLMs are as capable as evaluating each other as are humans with advanced degrees?
Re:Alpaca RLHF-ed to beat ChatGPT by jacooper on Tuesday May 23, 2023 @10:25PM (#36053346)
Also humans aren't exact clones
Re:Alpaca RLHF-ed to beat ChatGPT by anothernewdude on Monday May 29, 2023 @07:08AM (#36112791)
Yes. They're both awful.