AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
1min snip
LangChain’s Harrison Chase on Building the Orchestration Layer for AI Agents
Training Data
Training Models with Prompting Techniques
The development of prompting techniques like Chain of Thought emerged to address the limitation where LLMs struggled to reason about the first step of a task. These techniques provided LLMs with more space to think step by step, enabling them to train models to consider each step systematically. Sun Yiu's paper 'react' introduced a cognitive architecture for agents, emphasizing the importance of training models to think step by step in a task.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode