Hmm, that’s interesting. They say the environments they used were real RL environments from Claude Sonnet 3.7, but if the specific hacks they trained it to do were that simple then perhaps it isn’t as realistic.
Hmm, that’s interesting. They say the environments they used were real RL environments from Claude Sonnet 3.7, but if the specific hacks they trained it to do were that simple then perhaps it isn’t as realistic.