How outdated information hides in LLM token generation probabilities

Re:How outdated information hides in LLM token generation pr... by mistercow on Sunday January 12, 2025 @05:19AM (#42672510)

I’m not sure what kind of response you’re looking for, or if this is a rhetorical question or not. But “how could a language model infer…?” can be asked about a whole lot of things that language models have no problem reliably inferring.

[ Parent | on HN ]

Re:How outdated information hides in LLM token generation pr... by blueflow on Sunday January 12, 2025 @05:26AM (#42672536)

> that language models have no problem reliably inferring

... the article did give me a different impression.

[ Parent | on HN ]

Re:How outdated information hides in LLM token generation pr... by mistercow on Sunday January 12, 2025 @05:29AM (#42672544)

I don’t think you read my comment correctly.

[ Parent | on HN ]