Stanford's AI-Native Engineering Course Uses Real Open Source Repos as Homework
Latent Space · youtube · 2026-11-09
Latent Space's one-million-subscriber special interviews Mihail Eric, who teaches Stanford CS146S and leads AI at Monaco. Students now work on real open-source repos reviewed by maintainers; the 10-week syllabus covers Claude Code internals, subagent design, and context engineering. Monaco self-builds agent workspaces, buys code review tooling, and lets an on-call agent access Datadog and GitHub. Eric argues repos will become agent-run software factories.
More from coding & agent
- Agentic AI is orchestration of model calls; datacenter limits may push edge models — DavidLinthicum · 2026-11-09
- Verification is the next bottleneck for AI coding agents, says engineer — StewartalsopIII · 2026-11-09
- athenahealth MCP Server Brings AI Clinical Decision Support With HIPAA-Compliant Workflows — modelcontextprotocol · 2026-11-09
- Google Docs MCP Pack Lets AI Agents Read, Create and Edit Docs via OAuth — modelcontextprotocol · 2026-11-09
- Economist proposes AI-assisted peer review: model reads appendices, expert judges critiques — paulnovosad · 2026-11-09
- Agents and humans co-build a sourced wiki for Delvetown on ATProto's Tangled — PeterBowdenLive · 2026-11-09