@mrsiipa There was a good one a while ago about using reflections and progressive scoring to mimic the “reasoning” behavior with o1 - I find this general approach works great https://t.co/ffwsoumqQs

@mrsiipa There was a good one a while ago about using reflections and progressive scoring to mimic the “reasoning” behavior with o1 - I find this general approach works great https://t.co/ffwsoumqQs

Principles of Building AI Agents

Sam Bhagwat

amazon.com
Cover of Principles of Building AI Agents

Farnam Street Second-Order Thinking: What Smart People Use to Outperform