Working with Giant Language Fashions
For those who’re not a member however wish to learn this text, see this good friend hyperlink here.
Chain of Thought (CoT) has been round for fairly a while and is technically a kind of superior immediate engineering, however it stays related even now, a number of years after it was first launched. CoT, in its varied types, is often an effort to power giant language fashions to motive.
After the discharge of o1, we noticed the hype round these methods improve.
Nobody fully is aware of how o1 works (apart from OpenAI, that’s), whether or not it’s a mix system, what sort of information it has been fine-tuned with, if they’re utilizing reinforcement studying, or if there are a number of fashions working collectively.
Possibly one mannequin does the planning, one other the pondering, and a 3rd charges.
Nonetheless, there was numerous open analysis round this that you simply may wish to dig into. So for this piece, I’ll undergo what’s on the market. Naturally I’ll check the totally different CoT methods to see how and if we will obtain any actual enhancements.