←Story detail

Trending story Continuously updated

English text is being prepared.

3 reports1 discussions4 story updatesUpdated Oct 31 18:00

Understand this story

AI overview

Gabriel Ocana Santero, founder of Exin Therapeutics, described how the team used an AI agent to operate a self-built surgical device and complete a brain injection in a living mouse. The agent selected one of 19 gene therapy vectors, set the injection point at the lateral entorhinal cortex with coordinates taken from the average of three papers, and injected 250 nanoliters of the drug solution within five minutes, taking screenshots to observe 32 times throughout. Claude Opus 5.5, which the team tested first, refused to run as soon as it detected that the task involved a living organism; Opus 5 stopped at the in vivo step after simulating the full procedure; the model that ultimately carried out the task was Claude Sonnet 5. The craniotomy was still performed by humans, with safeguards including a veterinarian on site, manual approval of the injection plan, and a physical emergency stop switch. During the procedure, a fault occurred in the coordinate system; the agent recognized the positional error but did not change the code because its instructions prohibited it, so the team used a separate agent on Opus 5 to modify the code, and the surgery took more than an hour instead of the usual roughly 45 minutes.

AI-generated from public reports

Latest development · Report

AI agent performs brain injection experiment on a live mouse

Developments

1 confirmed developments

  1. Ocana-Santero says Claude agent autonomously selected gene therapy and performed mouse brain surgery

    Source:Phoenix Technology

Reports and discussion timeline

Browse reports and discussion by time. Their evidence levels remain distinct.

Oct 31

  1. Wired AI

    AI agent performs brain injection experiment on a live mouse

    Gabriel Ocana Santero, founder of the biotech company Exin Therapeutics, used an AI agent to operate a self-built surgical device and perform a brain injection on a live mouse. The team initially tested Claude Opus 5.5, but the model refused to guide the needle into the mouse's brain, fearing that stopping midway would endanger the animal, and they then switched to Claude Sonnet 5 to proceed. The experiment set up manual approval of the injection plan and an emergency power-off button, and restricted the agent from modifying the device's low-level code; during the process, a fault occurred in the coordinate system, and although the agent identified the position error, it did not change the code because instructions prohibited it, so the team separately used an agent on Opus 5 to modify the code, extending the surgery duration from the usual about 45 minutes to more than an hour.

  2. NumeramaRelated discussion

    Numerama joined this discussion

    This post contributes to heat; it is not a formal report or confirmed fact.

  3. Phoenix Technology

    Exin Therapeutics Uses AI Agent to Perform Brain Surgery on a Mouse; Opus 5.5 Refuses to Execute

    The Exin Therapeutics team used a surgical platform modified with Arduino to have an AI Agent perform brain injection surgery on a mouse; the model that ultimately carried it out was Sonnet 5. The Agent selected one of 19 gene therapy vectors, set the injection site at the lateral entorhinal cortex, took coordinates from the average of three papers, injected 250 nanoliters of solution within five minutes, and took screenshots for observation 32 times throughout. Opus 5.5, the team's initial choice, refused to run as soon as it detected that the task involved a living organism; Opus 5 simulated the complete procedure but stopped at the live-animal step. The craniotomy was still performed by a human, and human checkpoints such as a veterinarian on site and a physical emergency stop switch were in place.

  4. The Decoder

    Claude Sonnet 5 Autonomously Selects Gene Therapy and Completes Mouse Brain Surgery

    The research team had Claude Sonnet 5 autonomously select a gene therapy, brain region, and injection coordinates in an epilepsy mouse model, and operate custom surgical equipment to complete the injection, with a licensed veterinarian approving the irreversible steps throughout. The agent selected one of 19 candidate therapies—a regimen that enhances inhibitory signaling pathways—cross-checked three papers and took the average to determine the injection coordinates, and made 32 observations via camera during the procedure. After a mid-procedure connection loss, it judged that the target location exceeded the device's range of motion and refused to continue; this judgment was later proven correct, and the team ultimately had to manually modify the code to proceed; the more capable Claude Opus 5.5 and Opus 5 refused to perform the surgery. Ocana-Santero said there was no prior precedent of an agent autonomously selecting a treatment and brain target and carrying it out in a living mammal; the mouse recovered well, the technical report has not yet been released, and the results have not been peer-reviewed.

Heat trend for this story

Current
30
Period peak
34 Oct 31 19:00
24-hour change
—

Move the pointer or select the chart to inspect hourly heat. Use the left and right arrow keys with a keyboard.

Related stories

  1. Related storiesOpenAI announces ban on direct internet access for models during training
  2. Related storiesOpenAI says its models helped discover critical PHP security vulnerabilities
  3. Related storiesAnthropic releases Claude Opus 5.5
  4. Related storiesOpenAI launches GPT-6.1 Terra on ChatGPT Work and Codex