News for hackers. Stuff that matters.
Re:Open AI gets GPT-3 to work by hiring an army of humans to... by ironrabbit on Monday March 28, 2022 @02:56PM (#30834180)
Is there any evidence that GPT-3 responses are edited/filtered before being returned to users? My understanding is that some GPT-3 responses are annotated post-hoc, and this data is used to fine-tune later versions of GPT-3 (InstructGPT). This article seems extremely misleading.
Re:Open AI gets GPT-3 to work by hiring an army of humans to... by ImPostingOnHN on Monday March 28, 2022 @11:04PM (#30838276)
it seems there is evidence that GPT-3 is being overtrained in response to well publicized bad inputs, without regard to the generalizability of the PR-driven spot-edits, which is what the article describes