#141 – Richard Ngo on large language models, OpenAI, and striving to make the future go well

Large language models like GPT-3, and now ChatGPT, are neural networks trained on a large fraction of all text available on the internet to do one thing: predict the next word in a passage. This simple technique has led to something extraordinary — black boxes able to write TV scripts, explain jokes, produce satirical poetry, answer common factual questions, argue sensibly for political positions, and more. Every month their capabilities grow.<p> But do they really 'understand' what they're saying, or do they just give the illusion of understanding?</p><p> Today's guest, Richard Ngo, thinks that in the most important se...