Articles
Worth reading
A short take on pieces worth your time — architecture, AI, system design, and engineering careers — each one linked back to its original source.
9 articles
In-House LLM Serving at Netflix
Most companies just call a hosted LLM API and move on; Netflix's AI Platform team explains why and how they run the full inference stack themselves instead, inside their existing production environment rather than spinning up a separate ML silo. What's genuinely useful here is the decision-making, not just the architecture — the tradeoffs they weighed on cost, latency, and operational ownership before choosing to build rather than buy. Good grounding if you're evaluating whether your org actually needs to run its own inference infrastructure.
Securing the future of AI agents
Rohin Shah and Four Flynn lay out Google DeepMind's roadmap for securing their own internal systems against AI agents that are capable enough to be genuinely useful but not reliably aligned: access control, anomaly detection on agent trajectories, and human escalation for suspicious behavior, treated as security engineering problems rather than alignment philosophy. What struck me is that this isn't speculative; they describe an internal prototype already monitoring coding-agent trajectories in production. A useful, concrete counterpoint to AI safety discussions that stay abstract, this is what "securing an agent deployment" looks like as actual infrastructure.
What Is RAG? How Retrieval-Augmented Generation Works
A clear, current walkthrough of retrieval-augmented generation: why it exists (grounding an LLM in your own data instead of relying on what it memorized during training), how the retrieval-then-generate pipeline actually works, and where teams run into trouble in practice — the retrieval step, not the model, is almost always the real failure point. Useful if you're deciding whether RAG is the right pattern for a project, or just want a precise mental model instead of the marketing version.
Integrating Netflix's Foundation Model into Personalization Applications
Divya Gadde, Ko-Jen Hsiao, Dhaval Patel, and Moumita Bhattacharya walk through the three different ways Netflix integrated a single foundation model into multiple personalization surfaces, embeddings, subgraph, and fine-tuning, rather than training a bespoke model per use case. It's a practical answer to a question a lot of teams are facing right now: once you have one strong foundation model, how do you actually plug it into existing product surfaces without rebuilding everything downstream? The tradeoffs they lay out between the three integration patterns are transferable well beyond recommendation systems.
Effective Context Engineering for AI Agents
Anthropic's Applied AI team makes the case that context, not the prompt, is the scarcest resource in a production agent, and lays out concrete tactics for curating it: tighter tool definitions, deliberate compaction between turns, and structured note-taking instead of just stuffing more into the window. I've started treating "what's actually in the context window right now" as its own design question after reading this, rather than assuming bigger windows solve everything. A natural, more tactical follow-up to Anthropic's earlier "Building Effective AI Agents" piece.