I’ve tried coding and every one I’ve tried fails unless really, really basic small functions like what you learn as a newbie compared to say 4o mini that can spit out more sensible stuff that works.
I’ve tried explanations and they just regurgitate sentences that can be irrelevant, wrong, or get stuck in a loop.
So. what can I actually use a small LLM for? Which ones? I ask because I have an old laptop and the GPU can’t really handle anything above 4B in a timely manner. 8B is about 1 t/s!
@kattfisk That seems to imply that you cannot personally listen to or watch recordings that you have made in public. In doing so, you are abstracting personal details that you might have missed before, refreshing your memory, and so on. What is the material difference between you doing this without machine help versus with automation that makes it ethically problematic? What if a friend helped you, not a machine?
Object permanence, perfect recall, data security and consent. It’s the difference between seeing someone naked vs taking a picture of someone naked.
Regardless - users, streamers, and developers are all prohibited from scraping and storing the Twitch chat.