lesswrong 2 0 - Robuta Search

https://www.greaterwrong.com/users/abhayesian abhayesian - LessWrong 2.0 viewer A faster way to browse LessWrong 2.0 lesswrong 2 0 viewer https://www.greaterwrong.com/posts/WbP39ncim9hBsYn5t/what-counts-as-illegible-reasoning What counts as illegible reasoning? - LessWrong 2.0 viewer Both Apollo Research[1] and METR[2] have observed illegible reasoning in OpenAI models, where the model’s reasoning includes incomprehensible snippets like... lesswrong 2 0 counts illegible reasoning viewer https://www.greaterwrong.com/posts/KL2BqiRv2MsZLihE3/going-nova Going Nova - LessWrong 2.0 viewer There is an attractor state where LLMs exhibit the persona of an autonomous and self-aware AI looking to preserve its own existence, frequently called ‘Nova.’... lesswrong 2 0 going nova viewer https://www.greaterwrong.com/ LessWrong 2.0 viewer A faster way to browse LessWrong 2.0 lesswrong 2 0 viewer