News for hackers. Stuff that matters.
Re:The Coming of Local LLMs by whimsicalism on Tuesday April 11, 2023 @01:09PM (#35528020)
They just aren't quite close. Maybe you guys are asking shallow questions, but I'm asking subject matter questions and this is just not true.

It would be great if we could have detailed QA evaluation to show this, but of course then the open source people would train their models on it as a fine-tuning datasaet.

Re:The Coming of Local LLMs by UncleEntity on Tuesday April 11, 2023 @02:29PM (#35529200)
Train it on specific subject matter and not waste space on things like “what year did Jack Nicholson beat on that dude’s car with a golf club?”

I mean… the horror.

Re:The Coming of Local LLMs by whimsicalism on Tuesday April 11, 2023 @02:43PM (#35529443)
That's just not how these models work.
Re:The Coming of Local LLMs by taneq on Tuesday April 11, 2023 @05:34PM (#35531894)
You’ll have to forgive them, they’re probably trained mostly on HN posts. ;)