The LLama Effect: Leak Sparked a Series of Open Source Alternatives to ChatGPT

Re:The LLama Effect: Leak Sparked a Series of Open Source Al... by PoignardAzur on Sunday April 09, 2023 @06:29PM (#35507092)

That's not an answer.

The given question is one which requires some spatial reasoning to understand. By default, GPT can only understand spatial questions as described by text tokens which is a pretty noisy channel. So it's not obvious how GPT-4 could answer a spatial reasoning question (aside from memorizing it).

[ Parent | on HN ]

Re:The LLama Effect: Leak Sparked a Series of Open Source Al... by Method-X on Sunday April 09, 2023 @06:34PM (#35507144)

This is a good explanation: https://www.youtube.com/watch?v=qbIk7-JPB2c

[ Parent | on HN ]

Re:The LLama Effect: Leak Sparked a Series of Open Source Al... by qumpis on Sunday April 09, 2023 @08:05PM (#35507680)

Why does it require spatial reasoning if it can learn the (logical) rule of how the mirroring and glass doors behave?

[ Parent | on HN ]

Re:The LLama Effect: Leak Sparked a Series of Open Source Al... by lucubratory on Thursday April 13, 2023 @11:17AM (#35556789)

LLMs can build an internal world model and use it at inference time in order to understand spatial problems and rulesets. It's part of the often overlooked "How does it do that though?" counterpart to the often repeated "It's just predicting the next most likely token." Here's the write-up I've found that's the most clear, there are several other papers and ongoing research finding this though: https://thegradient.pub/othello/

[ Parent | on HN ]