News for hackers. Stuff that matters.
Re:Detecting hallucinations in large language models using s... by verdverm on Monday June 24, 2024 @01:22PM (#40778577)
Yann LeCun said something to the effect you cannot get reasoning with fixed computation budgets, which I found to be a simple way to explain and understand a hypothesized limitation
Re:Detecting hallucinations in large language models using s... by paraschopra on Wednesday June 26, 2024 @06:46AM (#40798477)
Nothing prevents you from doing chain of thought style unbounded generation.