0:00 Introduction to Autodev and Agent-based LLM Systems
0:48 Limitations of Co-pilot and the Need for Automation
1:10 Autodev Architecture Overview
2:01 The Role of the Conversation Manager and Agents
3:22 Demonstrating Autodev's End-to-End Flow
5:03 Comparing Autodev's Performance to GPT-4 Baseline
6:03 Autodev's Performance on the Human Eval Benchmark
6:37 Autodev's Performance on Test Generation
7:08 Conclusion and Wrap-up
arxiv.org/abs/2403.08299
vivekhaldar.com
x.com/vivekhaldar