News for hackers. Stuff that matters.

A comment on Internal representations of LLMs encode information about truthfulness. Parent comment

Re:Internal representations of LLMs encode information about... by ForHackernews on Wednesday October 30, 2024 @12:18PM (#41996886)
When I talk to philosophers on zoom my screen background is an exact replica of my actual background just so I can trick them into having a justified true belief that is not actually knowledge.

t. @abouelleill

[ Parent | on HN ]
Re:Internal representations of LLMs encode information about... by kelseyfrog on Wednesday October 30, 2024 @12:54PM (#41997410)
Are LLMs Gettier machines? I'm confident saying yes and that hallucinations are a consequence of this.

EDIT: I've had some time to think and if you read somewhere that Hartford is the capital of Connecticut, you're right in a Gettier way too. Reading some words that happen to be true is exactly like using a picture of your room as your zoom background. It is a facsimile of the knowledge encoded as words.

[ Parent | on HN ]