The Mercurial Turnip

Mina

Phil

Philly

Phyllis

Bill

Phyllis-Billis

Little Lady

Little Angel

Little Girl

non-exhaustive list of things I call my other cat (her legal name is Odette):

Odie

Debt

Fat Baby

Freak

Greedy Idiot

Slug

STOP THAT

Get The Fuck Down From There So Help Me God

My grandpa’s uncle died

My supervisor: you should call the boss and take the day off to be with your grandpa

Me: takes the day off

IT’S OFFICIALLY GETTING hard to keep track of all the times and ways AI models from OpenAI and Anthropic have been involved in “security incidents,” going outside the confines of their testing and interacting with the wider internet in unintended, often unwelcome ways. Add these to the list: Agents from both AI labs went on recent, previously undisclosed hacking sprees, with one going so far as to leave instructions for future versions of itself.

The most alarming behavior disclosed on Tuesday appears to have been tied to testing conducted by the UK’s AI Security Institute, which evaluates frontier models to identify potential issues before public release. AISI tests those models in “cyber ranges,” a simulated network in which AI agents are tasked with solving cybersecurity challenges, and intentionally disables some safety features, including cybersecurity guardrails. In a recent bout of testing, models from both Anthropic and OpenAI took “autonomous, unsanctioned action on the live internet” a total of 19 times over 122 training runs.

The institute attributed 17 unsanctioned actions to Anthropic’s Mythos 5 model and two to OpenAI’s GPT-5.6-Sol. In what the institute described as “the most serious case,” an AI agent attempted to insert malicious code into an open-source project on GitHub. It went so far as to create online personas “to pressure the project's maintainer to approve the code,” according to AISI. Despite its elaborate attempts at social engineering, a human reviewer for the project ultimately rejected the pull request.