Storm: LLM system that researches a topic and generates full-length wiki article

Post by jerf » Fri, Apr 12, 2024, 2:37 PM UTC

tossandthrow wrote: post #59

jerf wrote: post #50

Earlier quoted context omitted.

I'd go with "no", because people just consuming the output of other people is a big ongoing problem. Input from the universe needs to be added in order to maintain alignment with the universe, for whichever "universe" you are considering. Without frequent reference to reality, people feeding too much on people will inevitably depart from reality. In another context, you may know this as an "echo chamber". Not quite e…

yep, then we are back a "vaguely cynical hand-wringing about how bad AI is." currently we have mostly LLMs in the mix. but there are no reason that the Ai mix will not contain embodied agents thst also publish stuff in the internet. (think search and rescue bots that automatically write a report). Now Ai is connected to reality without people in the mix.

Post by JohnFen » Fri, Apr 12, 2024, 8:57 PM UTC

observationist wrote: post #78

lukev wrote: post #27

I can see this being useful iif the content is generated on demand and then discarded. Publishing AI generated material is generally speaking a horrible idea and does nobody any good (at least until accuracy levels get much much better.) Even if they do it well and truthfully (which they don't) current LLMs can only summarize, digest, and restate. There is no non-transient value add. LLMs may have a place to help que…

This is categorically untrue. Publishing material generated like this is going to be generally better than human generated content. It takes less time, can be systematically tested and rigorous, and you can specifically avoid the pitfalls of bias and prejudice. A system like this is multilayered, with prompts going through the whole problem solving process, considering the information presented, assuring quality and…