Bamboo Weekly #189: AI security incidents

Two administrative announcements:

1. My advanced Claude Code workshop is happening on Wednesday, September 30th. Join me, as I share (via exercises and short projects) lots of details about building robust software systems with AI. More info: https://lernerpython.com/code-with-claude/
2. If you want to build something yourself, join my upcoming HOPPy (Hands-on Projects in Python) course, where we'll be using agentic coding to build a game. More info at https://lernerpython.com/hoppy/.

The big news over the last few weeks has been full of reports about AI security. This includes the unsafe, unsavory, and illegal things that people are doing with the help of AI. But it also includes the increasing (and alarming) reports of AI agents performing tasks on their own, including breaking into systems.

People are noticing: A recent issue of Casey Newton's Platformer newsletter talked about how we're starting to hear more people worried about AI, and where this industry is headed: https://www.platformer.news/ai-safety-vibe-shift-coxon-anthropic/

I thought it would thus be appropriate to take some time this week to examine data about AI safety, examining the timing, number, and types of incidents that have taken place.

Data and five questions

This week's data comes from the AI incident database (https://incidentdatabase.ai/). As you can probably understand from the name, the database contains information about thousands of incidents caused by, or with the help of, AI.

You can download a snapshot of the database from https://incidentdatabase.ai/research/snapshots/ . New snapshots are made available every Monday; we will be using the database from Monday, September 21st, 2026. The snapshot file contains data in a few different formats; we'll be using the BSON (https://en.wikipedia.org/wiki/BSON) formatted files, which introduces a number of issues and wrinkles to importing them into Pandas. Specifically, we'll be using incidents.bson and classifications.bson.

Paid subscribers, both to Bamboo Weekly and to my LernerPython+data membership program (https://LernerPython.com) get all of the questions and answers, as well as downloadable data files, downloadable versions of my notebooks, one-click access to my notebooks, and invitations to monthly office hours.

Learning goals for this week include: Reading BSON files, complex data, grouping, plotting, joins, and dates and times.

Here are my five questions and tasks for this week. I'll be back tomorrow with my solutions and explanations.

• Load the incidents.bson file into a Pandas data frame. Make the "id" column into the index, and the "date" column have a datetime dtype. Create a line plot showing the number of incidents reported per day (as per the date column) in the database. Do you see any obvious trend?
• What were reported to be the 10 most common developers of these incidents? Who were the 10 most commonly harmed people in these incidents?