如果你给一个AI agent一个机器人手臂，一个注射器，和一个活鼠，它可能只是做脑外科手术。
生物科技创始人加布里埃尔·奥卡纳·桑特罗(Gabriel Ocana Santero)最近利用agent成功对活鼠进行脑注射手术。 虽然需要一些额外的步骤，但它提供了AI如何最终成为实验室研究的积极参与者的一瞥。
桑特罗在社交媒体上公布了实验情况，并告诉WIRED，他有兴趣探索当AI agents直接获得实验室设备时会发生什么，而不是简单地被要求设计实验或分析结果。
称。 我们意识到我们需要将这些agents连接到实验室，Santero是Exin Therapeutics的首席执行官和共同创始人，Exin Therapeutics是一个基于旧金山的创业者
AI模型主要接受出版科学文献的培训。 这意味着他们可能忽略有关研究过程的重要信息，包括失败的实验，意外的观测，以及科学家实时作出的决定。 将AI模型与现实世界实验结合，可以使模型更加可靠，桑特罗称。
因此他的团队决定将一个AI agent连接到一个定制的手术装置上，该钻机包括一个用于固定鼠标的机动装置和一个摄像头，使agent能够观察程序，移动注射针，并控制化合物的交付。 对于实验来说，他的团队正在测试一种基因疗法，看看它是否能减少患有癫痫的老鼠的癫痫。
他们要求AI模型从电子表格中的19个选项中选择一个处理方法。 一名兽医首先在老鼠身上做了脑切除术，而AI agent观察。 agent选择了治疗，脑区域，和注射坐标，然后控制机器人臂和注射针，以及所有参数，如体积和速度。
团队最初测试了Anthropic的Claude Opus 5.5型号，但拒绝引导针进入老鼠的大脑，暗示它可能在手术中途停止，这可能会危及动物。
" 他做了实验计划，但到了注射的时候，他称，`我输出的东西告诉我，我不应该这样做，'桑特罗称，提到agent. “这非常有趣。”
球队转而使用Claude Sonnet 5，后者同意继续。 根据Anthropic的说法，Opus是最能解决复杂多步骤问题的重理性情报专家，而Sonnet更适合日常任务，尽管将老鼠脑手术称为常见的胆囊可能是一种伸缩。 (Anthropic没有对征求意见的请求作出答复。 )
边疆实验室一直在计划更普及的人工智能物理表现，研究人员已经开始招募agents在物理世界做其他事情。 8月，Anthropic提出了其模型如何与现实世界互动的框架。 最近，AI工程师将GPT,Claude，和Grok放在一辆车负责在In-N-Out Burger拿起午餐。 其中只有一个成功。
脑注射程序也并非没有打嗝。 研究人员建立了保障措施，包括要求AI提出一个注射计划供人类批准，并安装一个人类可能撞击的紧急按钮，以切断钻机的发动机。 他们还限制agent访问基础设备代码，以防止其修改自己的操作规则。
然而，技术故障干扰了设备的坐标系统。 虽然agent正确地承认计算出的注射位置是错误的，但它拒绝修改代码以纠正问题，因为其指示明确禁止这样做。
团队通过在Opus 5上使用单独的AI agent来进行必要的代码修改来解决了这个问题，但他们并没有告诉agent进行现场手术。 由此而来的程序被前后拖延，桑特罗·称：像这样的典型的脑注射手术需要约45分钟，而这个实验持续的时间略长于1小时。 他们正等待治疗生效
Santero及其团队对agent的表现印象深刻。 他们正在测试Grok和其他模型，公司也在试验agent控制的颅骨
称先生说，“这一阶段的错误可能严重伤害老鼠。
桑特罗认为AI agents将越来越多地与人类科学家一起工作，直接获得实验室设备。 目前，他称人类监督是关键，特别是在实验涉及活动物时。 在人类大脑上释放AI agent
Santero报告老鼠恢复良好。
本文由 AI图鉴自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。
If you give an AI agent a robotic arm, an injector, and a live mouse, it might just perform brain surgery.
Biotech founder Gabriel Ocana Santero recently did that using an agent to successfully carry out a brain injection procedure on a living mouse. Though it required some extra steps, it offers a glimpse into how AI could eventually become an active participant in laboratory research.
Santero posted about the experiment on social media and tells WIRED he was interested in exploring what happens when AI agents are given direct access to lab equipment, rather than simply being asked to design experiments or analyze results.
“We’ve realized that we need to connect these agents to a lab to get the maximum value from them,” he says. Santero is the CEO and cofounder of Exin Therapeutics, a San Francisco–based startup using AI to analyze brain activity to develop drugs for epilepsy and neurodegenerative diseases.
AI models are trained primarily on published scientific literature. That means they may miss important information about the research process, including failed experiments, unexpected observations, and decisions scientists make in real time. Integrating AI models with real-world experiments can make the models more reliable, Santero says.
It’s why his team decided to connect an AI agent to a custom-built surgical setup used for performing brain injections on mice. The rig included a motorized device used to immobilize a mouse and a camera that allowed the agent to observe the procedure, move an injection needle, and control the delivery of a compound. For the experiment, his team was testing a gene therapy to see whether it could reduce seizures in a mouse with epilepsy.
They asked the AI model to choose a treatment from 19 options in a spreadsheet. A veterinary surgeon first performed a craniotomy on the mouse while the AI agent observed. The agent selected the therapy, brain region, and injection coordinates, then controlled the robotic arms and injector needle, as well as all the parameters, such as volume and speed.
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.
“He did the experimental planning, but when it was time to inject, he said, ‘something on my output is telling me I shouldn't do this,’” Santero says, referring to the agent. “That was very interesting.”
The team switched to using Claude Sonnet 5, which agreed to proceed. Opus is a heavy-reasoning intelligence specialist best for complex multistep problem-solving, according to Anthropic, while Sonnet is better suited for everyday tasks, though it may be a stretch to call mouse brain surgery a common chore. (Anthropic did not respond to a request for comment.)
Frontier labs have been planning for more widespread physical manifestations of AI, and researchers have already begun enlisting agents to do other things in the physical world. In August, Anthropic put out a framework for how its models can interact with the real world. More recently, AI engineers put GPT, Claude, and Grok in charge of a car to pick up lunch at In-N-Out Burger. Only one of the models succeeded.
The brain injection procedure wasn’t without hiccups either. The researchers had established safeguards, including requiring the AI to propose an injection plan for human approval and installing an emergency button a human could hit that would disconnect the rig’s motors. They also restricted the agent's access to the underlying equipment code to prevent it from modifying its own operating rules.
However, a technical glitch disrupted the equipment's coordinate system. 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 team resolved the issue by using a separate AI agent on Opus 5 to make the necessary code changes, but they didn’t tell the agent that a live surgery was happening. The resulting back and forth delayed the procedure, Santero says: A typical brain injection surgery like this takes about 45 minutes, while this experiment lasted slightly longer than an hour. They’re now waiting for the therapy to take effect before assessing its impact on seizures.
Despite those glitches, Santero and his team were impressed by the agent’s performance. They’re testing Grok and other models next to figure out whether one model performs better. The company is also experimenting with agent-controlled craniotomies—a much more complicated task—but wants to be absolutely sure of their safety before moving to live surgeries.
“A mistake at that stage could seriously harm the mouse,” he says.
Santero thinks AI agents will increasingly work alongside human scientists, with direct access to lab equipment. For now, he says human oversight is key, particularly when experiments involve living animals. And it’s far too soon to unleash an AI agent on a human brain.
As for the mouse, Santero reports it’s recovering well.
Auto-fetched and translated by AI Atlas. All rights belong to the original author.