News for hackers. Stuff that matters.
Re:Overcoming the Limits of Large Language Models by TeaBrain on Thursday July 18, 2024 @02:22PM (#40998358)
The problem with "incoherent output" is that it isn't describing the phenomenon at all. There have been cases where LLM output has been incoherent, but modern LLM hallucinations are usually coherent and well-contructed, just completely fabricated.
Re:Overcoming the Limits of Large Language Models by darby_nine on Friday July 19, 2024 @08:22AM (#41005663)
Do you have an example? Your statement seems trivially contradictory—how do you know it's fabricated without incoherence showing you this? Isn't fabrication the entire point of generative ai?
Re:Overcoming the Limits of Large Language Models by TeaBrain on Friday July 19, 2024 @09:55AM (#41006634)
It seems that your insistence upon using incoherence is based upon a misunderstanding of the word. Coherence does not mean to be factual, but to be logically ordered. Also, the word "fabricated" is generally used colloquially to describe made up information without factual basis.