Hacker News new | ask | show | jobs
by andreagrandi 906 days ago
Yeah, it’s fast but almost always wrong. I asked it a few things (recipes, trivia etc…) and it completely made up the answers. These things don’t really know how to say “I don’t know” and pretend to know everything.
2 comments

Can you provide specifics for what you asked what it answered? It seems to answer my questions, including recipes correctly.
I asked it to explain several plot points in the TV series "Foundation", and it got them wrong and admitted it when pressed. Several times. Specifically, why does Raych Foss kill Hari Seldon, and some follow-up questions.
Yeah, that's raw llama2 for you. Fine tuning, LoRa, that's how you get the nice responses.
I suspect this is Llama-2-chat and not the base model. It's very attuned to safety fine tuning, and it isn't having issues with completion in a chat format.

They probably weren't specific enough in mentioning what the model it was built on was, referring to Llama-2-chat as being a Llama-2 model (which is kind of correct).