News for hackers. Stuff that matters.

A comment on The LLama Effect: Leak Sparked a Series of Open Source Alternatives to ChatGPT. Parent comment

Re:The LLama Effect: Leak Sparked a Series of Open Source Al... by ascorbic on Monday April 10, 2023 @02:50AM (#35509798)
This is with 4. It did fine with the question, so I added another layer and it was fine:

A building has all signs in mirror writing. You are unable to read mirror writing. You come to a door and you read it and it says "pull". How should you open the door?

> Since the signs in the building are in mirror writing, and you are unable to read mirror writing, the word "pull" that you can read must be the mirror image of the actual instruction. The actual instruction should be the reverse, which is "push". So, you should open the door by pushing it.

[ Parent | on HN ]
Re:The LLama Effect: Leak Sparked a Series of Open Source Al... by BoiledCabbage on Monday April 10, 2023 @03:00AM (#35509841)
That's incredible.

It really seems more and more that the only way it can accurately predict text is to first build a model of reality.

[ Parent | on HN ]
Re:The LLama Effect: Leak Sparked a Series of Open Source Al... by fl7305 on Tuesday April 11, 2023 @03:23AM (#35521920)
If you want your LLM to predict the name of the murderer in a mystery novel, it can only do that reliably by understanding the text.
[ Parent | on HN ]