OpenAI's o1 model works best as a strategist that produces design documents and step-by-step plans, which other models like Sonnet 3.5 then execute. The speaker argues this division of labor between high-level reasoning and concrete tasks is the right way to use o1's strengths.
OpenAI shocked the world last week with a new model that is more intelligent than most humans. It comes in at 120 IQ points where all previous models were, somewhere around the 80 to 92 range. Here's the type of workflow in which you absolutely want to use this over any other AI then Mac actee here is saying the following. O1 mini is the architect. Explain my requirements and have it create a detailed design document with step by step instructions for each module. So O1 mini does the strategizing, the high level thinking, the step step by step planning and then he uses Sonnet 3.5 as the developer to actually write the code it generates. The code based on architectural document produced by O1 Mini. Let me tell you this is the correct workflow and this is the correct way to use it. Let 01 do the thinking, the strategizing, the brainstorming. Let it be the mastermind and then take what it produces and bring that over to another model that might be better at a concrete thing.
