Working with Large Language Models
If you’re not a member but want to read this article, see this friend link here.
Chain of Thought (CoT) has been around for quite some time and is technically a type of advanced prompt engineering, but it remains relevant even now, a few years after it was first introduced. CoT, in its various forms, is typically an effort to force large language models to reason.
After the release of o1, we saw the hype around these techniques increase.
No one completely knows how o1 works (except for OpenAI, that is), whether it’s a combination system, what kind of data it has been fine-tuned with, if they are using reinforcement learning, or if there are several models working together.
Maybe one model does the planning, another the thinking, and a third rates.
Nevertheless, there has been quite a lot of open research around this that you might want to dig into. So for this piece, I will go through what’s out there. Naturally I will test the different CoT techniques to see how and if we can achieve any real improvements.