JavaScript Jabber Can You Really Trust AI-Generated Code? - JSJ 699
9 snips
Dec 24, 2025 
Itamar Friedman, Founder of Codo, discusses the evolving role of AI in code generation and review. He explains that AI won't replace developers anytime soon but will change their workflows. The conversation covers how human oversight remains essential in verifying AI-generated code. Itamar also explores the importance of guardrails and quality standards, alongside the future of agent-driven development. Listeners learn about the balance between trusting AI and maintaining developer accountability in the coding process.
AI Snips
Chapters
Transcript
Episode notes
Code Review Is About Ownership
- Code review's core purpose is team ownership and collective responsibility for code.
- AI won't remove the need for humans to own, learn, and be accountable for production code.
Grow Skills Around AI Workflows
- Learn AI as a core developer tool: prompt, review, and own AI-produced artifacts.
- Specialize in higher-level tasks like specs, guardrails, and agent orchestration to stay valuable.
Use AI To Prioritize Human Attention
- Free humans from repetitive checks so they can focus on higher-value review tasks.
- Configure AI to surface the risky parts of a PR so reviewers spend time where it matters most.