2023-05-28 17:25 UTC
Replies (9)
-
@amsomniac@mastodon.mit.edu 2023-05-28 17:29
@Vrimj@mastodon.sandwich.net https://www.youtube.com/watch?v=gVvhxwtFsnE #nowplaying
-
@zippy1981@hachyderm.io 2023-05-28 17:50
@Vrimj@mastodon.sandwich.net lots of people in the technical-professional class do in fact just copy and paste a something from Google and don't know what it's actually doing for some subset of their job. They effectively are doing what chat gpt does.
-
@strwbrryJen@mastodon.social 2023-05-28 20:04
@Vrimj@mastodon.sandwich.net very much this
-
@LWFlouisa@cyberplace.social 2023-05-28 23:40
@Vrimj@mastodon.sandwich.net Excellent, I needed that image to brighten my mood. Lets talk to a plastic banana.
-
@PavelASamsonov@mastodon.social 2023-05-29 03:38
@Vrimj@mastodon.sandwich.net damn I really like "modeling outputs vs replicating a process" as a way to articulate the distinction
-
@kevinrns@mstdn.social 2023-05-29 04:46
@Vrimj@mastodon.sandwich.net It is "word complete while typing" with entire stolen books as the next letter.
-
@Techronic9876@sigmoid.social 2023-05-29 14:37
@Vrimj@mastodon.sandwich.net this is why chain of thought prompting completely surprised researchers working on LLMs. It seemed like using chain of thought replicated a process, and it possibly does for very simple processes Figuring out how to do bigger processes is the big question now
-
@awooo@pawb.fun 2023-05-28 17:49
@Vrimj@mastodon.sandwich.net I like this analogy! It shows that just like a real banana, there is a process behind it, but that it is a fundamentally different one that should have different expectations and uses.
-
@apaz@tech.lgbt 2023-05-29 04:23
@Vrimj@mastodon.sandwich.net In that case, how about chain of thought prompting? It's true that LMs only model an input/output distribution, but they can mimic and reproduce as many convincing artifacts along the way as necessary.