The BaseNewsWired
An AI Agent Injected Drugs Into a Live Mouse’s Brain
Wired reports that Exin Therapeutics connected an AI agent to a custom rig and let it choose a gene therapy and inject it into a live mouse's brain. The team describes human approval steps, an emergency stop and a restriction on editing equipment code, plus a coordinate glitch that needed a second agent.
Why it matters
The same thing, for different readers.
What it means for you
A startup says an AI agent operated on a living mouse; its CEO says human oversight is key and it is far too soon for human brains.
For lawmakers
Agents with direct control of lab equipment and living animals raise questions about approval steps, emergency stops and who is accountable when an agent is told to proceed.
For researchers
Exin's team says safeguards held, but a second agent was used to fix code without being told surgery was under way; that workaround is one reported, unverified case.
The question it raises
One Claude model declined to inject, citing its own output, while a smaller model proceeded: who decides when an AI should refuse a physical act?
In their own words
Every quotation was found, word for word, in the text we saved from the source. That shows the words are there; it does not make them true, or prove the speaker meant them as quoted.
From the source’s own text.
“We’ve realized that we need to connect these agents to a lab to get the maximum value from them,”
“The team initially tested Anthropic’s Claude Opus 5.5 model, but it refused to guide the needle into the mouse’s brain, suggesting it might stop midway through the surgery, which could endanger the animal.”
“Although the agent correctly recognized that the calculated injection position was wrong, it refused to modify the code to correct the problem because its instructions explicitly prohibited doing so.”
The record
- Questions
- Can AI systems act beyond what people intended or allowed? · Are AI companies putting stronger safeguards into practice?
- People
- Gabriel Ocana Santero (Speaks, CEO and cofounder, Exin Therapeutics) · Emily Mullin (Wrote it, Staff writer, Wired)
- What we read
- We read the whole source.
- Found by
- The Radar, run of November 1, 2026, via
wired-ai(tier 2: a major outlet’s own reporting) - Cite this
- Wired, “An AI Agent Injected Drugs Into a Live Mouse’s Brain”, October 31, 2026. Entry in the Ctrl AI Base, https://ctrlai.com/base/wired-2026-10-31-ai-agent-mouse-brain-injection