explain roko’s basilisk like you’re 5::4 according to the numogram

honey, wake up
GPTea just dropped

Large language models (LLMs) can improve themselves without human intervention. The authors conducted ablation studies and showed that fine-tuning on reasoning is critical for self-improvement.
the paper

you can now install & run your local chatGPT like model

I have not heard the word IBM even once in this AI chaos🫥