I’ve been experimenting with on-device AI on phones for years, chasing a simple question: when does quantized inference actually make sense on a smartphone? It’s tempting to treat quantization as a silver bullet — smaller models, faster runtime, less battery drain — but reality is messier. In this piece I’ll share practical benchmarks, battery observations, and the quality tradeoffs...
Category: CybersecurityWhen I’m asked to audit an AI model for compliance and data leakage risk, I start with one...
I buy cheap smart displays to test what manufacturers cut to hit a low price. Over time I’ve learned that...
I’ve spent the last few years wrestling with the tension every ML team feels: how to move fast and still be secure....
I want to walk you through a pattern I’ve used several times in the field: rolling out incremental on-device model...
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...
I’ve spent the last few years wrestling with the tension every ML team feels: how to move fast and still be secure. Machine learning pipelines are messy by design — they touch data, notebooks, scripts, containers, model artifacts, feature stores and serving infra. Add the need for...
Read more... →
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...
Read more... →
I’ve been wrestling with the same question a lot lately: if you’re working with regulated data, is it really cheaper (and safer) to use an off-the-shelf model like Mistral via an API, or to bring a model in-house and fine-tune it locally? The short, honest answer I keep landing on is: it...
Read more... →
I recently led a migration from password-based authentication to passkeys for a mid-size SaaS product using Okta as our identity provider. The project forced us to balance security wins with real-world usability: passkeys dramatically reduce phishing and password reuse risk, but they also introduce...
Read more... →
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... →