According to the paper "Stealing reasoning traces from proprietary llms" [0] all frontier models overthink.
Thinking is good.
You just don't see it in proprietary harnesses because it's literally cryptographically hidden from you.
According to the paper "Stealing reasoning traces from proprietary llms" [0] all frontier models overthink.
Thinking is good.
You just don't see it in proprietary harnesses because it's literally cryptographically hidden from you.