News for hackers. Stuff that matters.
Re:The genie escapes: Stanford copies the ChatGPT AI for les... by simonw on Monday March 20, 2023 @06:32PM (#35239785)
This is why Alpaca is a big deal: it shows what LLaMA can do after it's been fine-tuned to follow instructions like ChatGPT has.
Re:The genie escapes: Stanford copies the ChatGPT AI for les... by f_devd on Monday March 20, 2023 @06:54PM (#35240020)
Alpaca uses Self-Instruct[0] which is better than just the pre-training but I wouldn't expect it to be at the level of ChatGPT (RLHF) in terms of human-friendly prompting. OpenAssistant should make it close to ChatGPT (from GPT-3.5 version) if the LLaMA is as powerful as claimed.

[0]: https://arxiv.org/abs/2212.10560