Never Trust a Monkey: from AI Gobbledygook to Deployable Code
summary
The talk examines risks of relying on generative AI that produces unreliable or messy output and shows how to turn that output into production-ready code. It covers practical techniques, tooling, and workflows for validating, testing, and integrating AI-generated code so teams can safely deploy it.
AI-written summary · about
chapters (10)
- 0:00Introduction
- 1:55Intent to code gap
- 9:01AI code failures
- 16:31Trust in software
- 23:55Never trust a monkey
- 27:13Spec-driven limits
- 33:17Behavior-driven testing
- 43:43Intent integrity chain
- 50:30Demo and project
- 51:54Key takeaways
related talks
51mNever Trust a Monkey: The Chasm, the Craft, and the Chain of AI-Assisted Code
48mNever Trust a Monkey: The Chasm, the Craft & the Chain of AI-Assisted Code
39mBack to Basics: Cutting Through the AI-Generated Code Noise
55mAI Showdown: The Good, The Glitchy, and The Risky
32mEscape the Try-Again Loop: Verifying AI-Generated Code
32mHow to Make AI Work for You: A Deep Dive Guide into ChatGPT for IT Professionals
42mCode Without Caution: AI's Path to the Next Digital Disaster
56mPANEL: Unleashing the Future: The Impact of Gen AI on Development Productivity