Stanford CS146S Teaches AI-Native Engineering via Code Reviews
First merged summary.
Podcast with Mihail Eric discusses Stanford CS146S, where students review open-source patches, and Monaco's agent workflows for code review.
Stanford CS146S requires students to review unfamiliar open-source repositories, propose changes, and explain patches to maintainers. The nine-assignment course with capstone covers context engineering and diff understanding. Mihail Eric, who leads AI at Monaco and hosts the AI Engineer YouTube channel with one million subscribers, explains agent workspaces, code review tools, Datadog and GitHub access, and why code review becomes a bottleneck when AI generation outruns review. Human work remains focused on understanding design decisions.
- Stanford CS146S has nine assignments and a capstone
- Students review and explain open-source patches to maintainers
- Monaco uses custom agent workspaces for code review and debugging
- Agents like Hal investigate outages at Monaco
- Code review bottleneck when generation outruns review
- Syllabus covers context engineering and diff understanding
What each outlet adds
beyond the shared facts- Latent SpaceDetailed syllabus discussion, Monaco agent workflows, and Datadog GitHub access; shorter version adds nine assignments and capstone
Coverage
oldest first · one row per article · UTC- · 2d ago
Latent SpaceFirst report
Stanford CS146S teaches AI-native engineering via open-source maintainer reviews
Podcast with Monaco's AI lead discusses Stanford course where students review open-source code for AI agents.
- · 2d ago
Stanford teaches AI-native engineering with coding agents
Mihail Eric shares Stanford CS146S syllabus and Monaco agent workflows.