News for hackers. Stuff that matters.
Re:LLM Daydreaming by MrScruff on Wednesday July 16, 2025 @06:59AM (#44580815)
Yes, it seems like LLMs are system one thinking taken to the extreme. Reasoning was supposed to introduce some actual logic but you only have to play with these models for a short while to see that the reasoning tokens are a very soft constraint on the models eventual output.

Infact, they're trained to please us and so in general aren't very good at pushing back. It's incredibly easy to 'beat' an LLM in an argument since they often just follow your line of reasoning (it's in the models context after all).

Re:LLM Daydreaming by cantor_S_drug on Sunday July 20, 2025 @09:18AM (#44624970)
This is also true in a sense nuance will dropped in the compression mechanism and overrepresentation in the training data will get more weightage to be retained.