Small Models = Big Flexibility
OpenPipe
Small Models = Big Flexibility
0:48
Beyond Accuracy: Why Smaller, Specialized Models Matter
OpenPipe
Beyond Accuracy: Why Smaller, Specialized Models Matter
0:48
How do you successfully train a model with RL?
OpenPipe
How do you successfully train a model with RL?
0:46
What is Reinforcement Learning?
OpenPipe
What is Reinforcement Learning?
1:00
Panel: Deploying Enterprise AI Agents Securely
OpenPipe
Panel: Deploying Enterprise AI Agents Securely
30:25
Fast, Local, and Teachable: Why the Future of Real-World Agents is Small and Local by Vik Korrapati
OpenPipe
Fast, Local, and Teachable: Why the Future of Real-World Agents is Small and Local by Vik Korrapati
25:41
Will Brown: Abstractions for Agentic RL
OpenPipe
Will Brown: Abstractions for Agentic RL
31:08
Panel: Lessons Learned from Building Enterprise AI Agents
OpenPipe
Panel: Lessons Learned from Building Enterprise AI Agents
36:23
Building Reliable Agents with RL – Kyle Corbitt, CEO of OpenPipe
OpenPipe
Building Reliable Agents with RL – Kyle Corbitt, CEO of OpenPipe
28:11
Roadmap for the ART (Agent Reinforcement Trainer) Project
OpenPipe
Roadmap for the ART (Agent Reinforcement Trainer) Project
0:57
Training Agents with RL
OpenPipe
Training Agents with RL
59:32
Evals Best Practices for GenAI Apps | w/ Freddie Vargus Co-Founder and CTO @ QuotientAI
OpenPipe
Evals Best Practices for GenAI Apps | w/ Freddie Vargus Co-Founder and CTO @ QuotientAI
1:10:52
Production Grade Agent Eval Systems | w/ Nir Gazit Co-Founder @ Traceloop
OpenPipe
Production Grade Agent Eval Systems | w/ Nir Gazit Co-Founder @ Traceloop
51:31
Evaluating AI Agents via "Trajectory Evals" & "Eval Agents" | w/ Dhruv Singh Co-Founder @ HoneyHive
OpenPipe
Evaluating AI Agents via "Trajectory Evals" & "Eval Agents" | w/ Dhruv Singh Co-Founder @ HoneyHive
53:07
Building LLM Evaluation Systems in Prod | A Conversation w/ Wyatt Marshall Co-Founder of Halluminate
OpenPipe
Building LLM Evaluation Systems in Prod | A Conversation w/ Wyatt Marshall Co-Founder of Halluminate
47:46
Why “Control” is the Most Important Factor Driving Open Source LLM Fine-tuning
OpenPipe
Why “Control” is the Most Important Factor Driving Open Source LLM Fine-tuning
0:59
Performance Tradeoffs: Fine-tuning OpenAI vs Open Source LLMs
OpenPipe
Performance Tradeoffs: Fine-tuning OpenAI vs Open Source LLMs
1:00
Fine-tuning Best Practices Interview with Kyle Corbitt (Chapter 2: Models)
OpenPipe
Fine-tuning Best Practices Interview with Kyle Corbitt (Chapter 2: Models)
24:33
What does your training data actually look like?
OpenPipe
What does your training data actually look like?
1:00
Fine-tuning Best Practices Interview with Kyle Corbitt (Chapter 1: Training Data)
OpenPipe
Fine-tuning Best Practices Interview with Kyle Corbitt (Chapter 1: Training Data)
27:26
The Ten Commandments of Fine-Tuning
OpenPipe
The Ten Commandments of Fine-Tuning
32:02