Crazy that even o1-preview gets most things wrong.
This is in line with my own personal experience with LLMs and non-trivial questions. They’re excellent when answering questions on topics you know nothing about, and somehow embarrassingly wrong when you actually know the answer yourself…
It’s not clear to me why we’re still trying to encode all of human knowledge in a single model, instead of teaching the model how to look for answers from an external source (e.g. RAG).
This is in line with my own personal experience with LLMs and non-trivial questions. They’re excellent when answering questions on topics you know nothing about, and somehow embarrassingly wrong when you actually know the answer yourself…
It’s not clear to me why we’re still trying to encode all of human knowledge in a single model, instead of teaching the model how to look for answers from an external source (e.g. RAG).