Daniel Grady on Mythryl: “Imagine that AI labs had called it "spew" instead of "Chain of…”

Imagine that AI labs had called it "spew" instead of "Chain of Thought." "When we allow the model to increase its spewage, the final answer tends to be more useful." Does that make Anthropic's new paper more or less interesting? www.anthropic.com/research/rea...

anthropic.comReasoning models don't always say what they thinkResearch from Anthropic on the faithfulness of AI models' Chain-of-Thought

4/4/25, 8:59 pm0 reposts0 likes

Post