@Acetamide This has been coming for a long time, I'm glad the community is being a chance to move on to spaces which aren't just trying to suck blood.
relaxdontdoit
joined 1 year ago
@radarsat1 @nutomic I'm still working this out myself, but you can browse Lemmy on any account, and then comment from your mastodon account by searching the commenter (@radarsat1 in the search field did it for me), and then replying to them on mastodon. Pretty cool how it's linked, plenty of opportunities to build apps that make interacting between servers easier.
@Gaywallet I'm coming to think that expecting models to produce human-like values and underlying representations is a mistake, and we should recognize them as cognition tools which are entirely possible to misuse.
Why? LLMs get worse at tasks as you attempt to train them with RLHF - and those with the base models will use them without filtering for a significant intelligence-at-scale advantage. They'll give the masses the moralized, literally dumber version.