Completed
00:00 Introduction to Haizing
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Fuzzing in the GenAI Era - AI System Evaluation and Quality Assurance
Automatically move to the next video in the Classroom when playback concludes
- 1 00:00 Introduction to Haizing
- 2 01:16 The "Last Mile Problem" in AI
- 3 02:47 The Brittleness of GenAI Applications
- 4 03:54 Examples of Brittle Chatbots
- 5 04:29 Inadequacy of Standard Evaluation Methods
- 6 06:09 Haizing: Simulating the Last Mile
- 7 08:43 Scaling Evaluation with Agents as Judges
- 8 09:29 Verdict: Accuracy vs. Latency
- 9 11:47 Scaling Evaluation with RL-Tuned Judges
- 10 14:06 Fuzzing vs. Adversarial Testing in AI
- 11 14:37 Simulation as Prompt Optimization
- 12 16:23 Case Study: Haizing a Major European Bank's AI App
- 13 17:05 Case Study: Haizing a F500 Bank's Voice Agents
- 14 17:46 Case Study: Scaling Voice Agent Evals with Verdict
