I want to walk you through a pattern I’ve used several times in the field: rolling out incremental on-device model updates using delta-only packages so users get improvements with minimal bandwidth, storage and downtime. I’ve shipped mobile and embedded updates for everything from speech models to small vision networks, and the trick isn’t rocket science—it's about thinking in deltas,...
I’ve been wrestling with the same question a lot lately: if you’re working with regulated data, is it really...
I recently led a migration from password-based authentication to passkeys for a mid-size SaaS product using Okta as our...
Keeping an LLM on-device up to date in a field app is deceptively hard. Over-the-air model updates, prompt tuning...
I’ve been benchmarking vector databases for months now, because keeping semantic search realtime at scale is one of...
I remember the first time my team relied on an AI system in production: a recommendation model that quietly drifted for...
Embedding drift is one of those slow, sneaky problems you don’t notice until your semantic search suddenly returns...
Keeping an LLM on-device up to date in a field app is deceptively hard. Over-the-air model updates, prompt tuning patches, and delta compression can change user experience, storage, and — critically — battery life. I've worked through many update flows, from enterprise fleet deployments on...
Read more... →
I’ve been benchmarking vector databases for months now, because keeping semantic search realtime at scale is one of those problems that sounds simple until you try to run it on real traffic. In this article I walk through the tests I ran comparing Qdrant, Milvus, and Pinecone focusing on three...
Read more... →
I remember the first time my team relied on an AI system in production: a recommendation model that quietly drifted for weeks until business metrics diverged and users complained. We had alerts—sort of—but they told us symptoms, not causes. That experience shaped how I evaluate AI observability...
Read more... →
Embedding drift is one of those slow, sneaky problems you don’t notice until your semantic search suddenly returns garbage for queries that used to work. I’ve wrestled with it in production: models change, content evolves, third-party data pipelines get tweaked, and the embeddings that once...
Read more... →
I spent the last two weekends tearing down the privacy posture of three affordable Wi‑Fi 6E mesh systems so you don’t have to. The promise of 6GHz bandwidth and smoother multi-device performance is great, but if a router phones home constantly, exposes diagnostics to a vendor cloud, or forces...
Read more... →
I’ve been experimenting with on-device GPT-style models on phones and tablets for over a year now, trying to answer the question that keeps coming up in meetings, DMs, and comment threads: can on-device GPT replace cloud inference for offline mobile apps? The short answer is: sometimes — but...
Read more... →
I’ve been watching models quietly change behavior in production long enough to know the moment a product team tells me “we didn’t see it coming.” Silent model drift — where performance degrades without obvious feature changes or clear data pipeline failures — is the kind of slow leak...
Read more... →
I’ve spent the last few years helping teams build real-time features—live dashboards, multiplayer sessions, collaborative editors—and one thing keeps coming up in post-launch retrospectives: egress bills. Real-time apps are chatty by design, and pushing bits out of a cloud region to end-users...
Read more... →
I recently spent a few weekends trying to answer a practical question I keep getting from field engineers and IT managers: can you run a reliable on-device LLM for field techs on a Raspberry Pi 5? The short answer is: yes—with important caveats. In this piece I’ll walk you through the realistic...
Read more... →
I installed my first smart home hub because I wanted fewer apps, fewer latency issues, and — frankly — fewer cloud services hoarding sensor data about what I do at home. Over the years I’ve tested hubs that promise “local-first” operation and those that lean on cloud conveniences, and...
Read more... →