News for hackers. Stuff that matters.
Re:Show HN: Alpaca.cpp – Run an Instruction-Tuned Chat-Style... by Fomite on Thursday March 16, 2023 @05:38PM (#35189075)
This is one of the things that LLMs seem to be struggling with. They're very good at tone, and feeling right without actually being write.

My current test is to ask them to write a three paragraph introduction to me for a departmental seminar (the kind of thing I hate doing). Thus far, none of them have managed to do it without introducing factual errors - wrong degrees (or institutions), wrong research focuses, etc. But they're all credible sounding in their wrongness.

Re:Show HN: Alpaca.cpp – Run an Instruction-Tuned Chat-Style... by bleuchase on Thursday March 16, 2023 @06:49PM (#35190010)
> They're very good at tone, and feeling right without actually being write.

The text they generate is probably free of errors like this one as well

Re:Show HN: Alpaca.cpp – Run an Instruction-Tuned Chat-Style... by Fomite on Friday March 17, 2023 @12:31AM (#35193143)
Probably.
Re:Show HN: Alpaca.cpp – Run an Instruction-Tuned Chat-Style... by bleuchase on Friday March 17, 2023 @04:11AM (#35194494)
I’m sure someone is working on adding support for human-like errors in LLM outputs.
Re:Show HN: Alpaca.cpp – Run an Instruction-Tuned Chat-Style... by crucialfelix on Friday March 17, 2023 @06:19AM (#35195181)
Write a crappy intro for yourself with all the facts included.

Ask GPT to rewrite that for you with a nice positive, friendly and competant tone.

It's really good at that.