Notes on OpenAI’s new o1 chain-of-thought models

OpenAI recently released two new preview models, o1-preview and o1-mini, emphasizing enhanced reasoning capabilities through a 'chain of thought' approach. These models, designed to spend more time thinking before responding, introduce some major trade-offs in costs and performance. They have impressive advancements in handling complex prompts and reasoning but lack transparency in their reasoning process due to hidden reasoning tokens.

Visit Original Article →