AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
AI Alignment Is Trivial
We have already seen chat GPT 3.5 in those English at the level of a college educated person and has very little knowledge about arithmetic. Can't even do simple arithmetic. In humans, that kind of a discrepancy is very unusual. So people who look at the earliest LLMs and their behaviors, they are basically saying that this is very strange. This got to be wrong. But if we accept that these skills such as arithmetic and English are very separable, we can look at what else the system has in the way of skills. And we notice that all behaviors are just skills. You can learn to snowboard, you can learn Finnish language, there's all kinds of stuff that