In this mega-post, you'll dive into the world of AI evaluations and how they might be used to evaluate privacy. This is a developing area of research and practice, so there aren't established best practices industry-wide just yet.

However, there are a growing set of practices to start, useful advice …

A few months ago, NVIDIA CEO Jensen Huang announced their version of NanoClaw, which promised to offer better privacy, security and performance compared to the popular open-source tool OpenClaw. OpenClaw, an agent framework with easy tooling, was mired with numerous security and privacy problems involving loss of sensitive data like …

There's been a lot of chatter about guardrails that's more marketing than science, so here's a real take on guardrails so that you can make real decisions about y:our machine learning architecture.

Note that this is a mega-post that I'm going to keep updated with the latest references. Should …

If you've read Practical Data Privacy, you'll know I'm not a huge fan of synthetic data. As a data scientist and machine learning person, usually I want to use high quality data and only introduce slight deviations by using protections for privacy (like differential privacy).

In my book, I clarify …

I've been exploring privacy and security aspects of AI-assisted coding and also experimenting with those workflows for my own work. In doing so, I've got a pretty robust setup for using Claude Code with both the Anthropic backend and a locally hosted GPU machine in my at home AI lab …

AI usage (both intended and not) is increasing in our products, software and lives. For some, this is a welcome way to automate tedious tasks; for others, an intrusion that doesn't seem to end. For everyone, AI changes how you might think about and evaluate data privacy.

At workplaces, there's …

You've learned in the last few articles about how differential privacy works and some of the common pitfalls of actually using it in deep learning scenarios.

In this article, you'll learn about tracking differential privacy: through parameter choice, accounting and auditing. If done well, these choices and methods reduce memorization …

If you're just getting started with local AI and local-first development, one of the initial hurdles will be getting your data local.

More of an audio-visual person? Check out the accompanying YouTube video on the Probably Private channel if you'd rather watch and listen.

Why should you store data locally …

So, you wanna do at-home AI? Yes, you do!

There's a bunch of great reasons to run your own AI including having more control over your data and models, learning more about how deep learning works, testing out new ideas without having to pay extra cloud or subscription costs and …

In the last article in the series on addressing the problems of memorization in deep learning and AI, you learned about differential privacy and how to apply it to deep learning/AI systems. In this article, you'll explore what can go wrong when using differential privacy training in deep learning …