Researcher had Claude Sonnet 5 perform brain surgery on a live mouse
According to the researcher, Claude Sonnet 5 independently chose an epilepsy treatment method and performed a brain injection in a live mouse, while Opus 5 and Opus 5.5 refused because the task involved real biological objects.
Researcher had Claude Sonnet 5 perform brain surgery on a live mouse
The goal was to treat epilepsy and reduce the number of seizures.
Here is what Claude did:
- Considered 19 possible treatments and selected one that enhances the action of a natural brain substance responsible for inhibition and calming.
- Determined the injection site based on the presumed seizure origin.
- Calculated the drug delivery point by averaging data from three scientific studies.
- Lowered the needle to a depth of 4.3 mm into the mouse brain.
- Over five minutes, delivered a dose of roughly 1/20,000 of a teaspoon.
- Checked the live camera image 32 times to monitor possible complications, including bleeding.
The mouse regained consciousness after the operation and recovered successfully.
Notably, Opus 5.5 and Opus 5 refused to perform the task because it involved real biological objects. The task was ultimately assigned to Sonnet 5.
According to the researcher, as far as he knows, this is the first case where an AI system independently chose a treatment method and then performed an injection directly into the brain of a living mammal.
Why it matters
AnalysisIt shows how AI assistants may move beyond text tasks toward autonomous biomedical decisions, while raising urgent questions about safety, ethics, and oversight of procedures involving living organisms.
Discuss in community
Share your questions and insights with developers
Related in Ecosystem
Practical guides, core terminology, and agent skills
Researcher lets Claude Sonnet 5 perform brain surgery on a live mouse
According to the researcher, Claude Sonnet 5 independently selected an epilepsy treatment and performed an injection into a live mouse’s brain.
Experimental Claude AI Model Found Vulnerabilities in Chrome, Safari, Android, Windows and Linux
Anthropic published results of testing its experimental Claude AI model, including 62 Chrome vulnerabilities, a Safari exploit and a 53-minute Linux kernel root exploit.
Markdown Format: The Complete Guide for AI Workflows and Automation
A comprehensive hands-on guide to Markdown syntax for AI development: CommonMark standards, heading hierarchy, GFM tables, character escaping, system prompts, and CLAUDE.md guidelines.
Computer Use via AI
Anthropic's technology (introduced in Claude 3.5 Sonnet) enables neural networks to control operating systems like a human: taking screenshots, analyzing window coordinates, moving the mouse cursor, clicking buttons, and entering text without using specialized APIs.