https://vincentherrmann.github.io
How can we tell if an LLM is actually "thinking" versus just spitting out memorized or trivial text? Can we detect when a model is doing anything interesting?
(Thread below👇)
How can we tell if an LLM is actually "thinking" versus just spitting out memorized or trivial text? Can we detect when a model is doing anything interesting?
(Thread below👇)