Fernando Irarrázaval

What happened after 2,000 people tried to hack my AI assistant

Thu, 25 Jun 2026 00:00:00 +0000

I built hackmyclaw.com, where anyone could email Fiu, my OpenClaw assistant, and try to make it leak the contents of a secrets.env file.

After reaching the front page of Hacker News, Fiu received more than 6,000 emails from over 2,000 people trying to break it.

The secrets never leaked. No attacker managed to make Fiu send an unauthorized reply.

The setup

I enjoy using OpenClaw and Hermes, but I’m also concerned about the security implications. AI assistants have access to emails, calendars, files, and the web. If an attacker can trick your AI into doing something it shouldn’t, that’s bad news.

Why Bayesian Statistics

Fri, 23 Jul 2021 00:00:00 +0000

It is hard to describe the benefits of Bayesian statistics. So let me show them by describing a problem I solved using Bayesian statistics, which would be hard to solve with traditional statistics.

The problem

When COVID struck, Enveritas helped governments measure how fast the disease was spreading.

Since this was early in the COVID pandemic, there wasn’t a lot of data about how widespread COVID-19 was in Ethiopia, rural areas, and Africa in general. Without data, governments couldn’t decide: should they lock down?

The reason I am using Altair for most of my visualization in Python

Sat, 04 May 2019 00:00:00 +0000

Sadly, in Python, we do not have a ggplot2.

Python’s go to visualization library, matplotlib, is very powerful¹ but has severe limitations. At times its flexibility is a blessing, but it is easy to get frustrated adding a small feature to your graph. Also, matplotlib dual object oriented and state-based interface is confusing. I still don’t completely grasp it even though I have been using matplotlib for years. Lastly, it makes only static graphs.