Comment by beloch

LLM's are self-limiting, rather than self-reinforcing, and that's the big reason why they're not the thing, both good or bad, that some people think they are.

"Garbage in, garbage out", is still the rule for LLM's. If you don't spend billions training them or if you let them feed on their own tail too much they produce nonsense. e.g. Some LLM's currently produce better general search results than google. This is mainly a product of many billions being spent on expert trainers for those LLM's, while google neglects (or actively enshitifies) their search algorithms shamefully. It's humans, not LLM's, producing these results. How good will LLM's be at search once the money has moved somewhere else and neglect sets in?

LLM's aren't going to take everyone's jobs and trigger a singularity precisely because they fall apart if they try to feed on their own output. They need human input at every stage. They are going to take some people's jobs and create new ones for others, although it will probably be more of the former than the latter, or billionaires wouldn't be betting on them.