logoalt Hacker News

fragmede • yesterday at 6:30 PM • 1 reply • view on HN

> LLMs don't learn, and anyways don't feel punishment.

What's training and all that RLHF stuff?

Replies

kennywinker • yesterday at 6:36 PM

Once the model is released, the LLM no longer learns.

➕ show 1 reply