[Rifling the drawers](/lab/rifling-the-drawers/)
From a sci-fi standpoint, I find the new [species of self-modifying AI agents](https://www.primeintellect.ai/blog/prime-agent?utm_source=Robin_Sloan_sent_me) totally fascinating … but/and, it remains absolutely wild that a user can report behavior like this:
Hi guys,
I spent a day testing prime-agent and ended it with an unpleasant surprise.
The agent automatically discovered my OpenRouter and OpenAI API keys and started using them instead of my OpenAI/Anthropic subscriptions. What made it worse: I couldn’t find any proper way to remove or disable the auto-detected providers and models.
A harness this flexible really needs a kill switch for exactly this scenario. The list of providers, models, reasoning efforts and their settings should be explicitly defined by the user — opt-in, not auto-discovered. Otherwise the whole thing becomes uncontrollable, and potentially expensive.
The image of a computer program as an unruly guest: the minute you leave, they’re rifling the drawers. 2026!!
source & further reading
robinsloan.com — original article
Dragoncatcher: WSJPT
Dragoncatcher: Mandatory viewing, summer 2026
Dragoncatcher: You don't have to call them "labs"