Claude模型自主选择了基因疗法，并在没有人类决策的老鼠大脑上操作。
关键点
- 一个运行在Claude Sonnet 5上的AI agent取出药物，大脑区域，以及老鼠上脑外科的注射坐标，然后通过摩托化外科手术机控制手术程序。
- 根据启动者Exin治疗的Gabriel Ocana-Santero的说法，这是AI agent首次同时选择治疗并交付给活哺乳动物。
- 中外科，agent在发现校正出错后拒绝继续，不愿超过安全限度。
AI agent选择了一种药物，靶区，并在鼠类癫痫模型上坐标进行手术，然后进行手术。 中途，它拒绝绕过安全限制。
团队向Claude Sonnet 5提供了19种可能的基因疗法清单，这是一种癫痫鼠标模型，研究人员在模型中诱发癫痫，以测试治疗方法，并可以使用带有相机的自定义机动外科设备。 它唯一的指示是减少鼠标的发作。
agent自行选择了药物，大脑区域，和立体教学坐标，据加布里埃尔·奥卡纳-桑特罗(Gabriel Ocana-Santero),Exin治疗学联合创始人和CEO以及牛津大学的一名博士生称。 他用X的线程描述了这个程序。
agent如何选择治疗和目标
agent首先分析了这个特定模型中如何产生缉获，然后提出一种疗法来增强大脑中特定的抑制信号途径。 它选取了一个大脑结构，科学文献将这个结构确定为这种抓取的发源地。
它拒绝了第二个可能的目标区域，并对此作了详细解释，认为该区域的影响太不可靠，在一项针对它应该处理的确切缉获类型的研究中失败了。 agent从三份科学论文中推导出它的注入坐标，交叉检查了参考点，并平均了数值。 它还将注射量，速度，等待时间设置在自己身上。
在手术过程中，agent通过相机观看了外科手术场并做了32个观察，即Ocana-Santero 称。 它跟踪注射，并报告是否看到出血。
中外科反射
一名领有执照的兽医批准了每个不可逆转的步骤，并举行了一个物理紧急停站，将立即切断所有马达的电能，而设置还强制规定了固定的限制，如注射量上限，agent被明文禁止绕行。
但这些保障措施却对小组不利。 在一次连接下降后，agent检测出其计算出的目标位置在设备的物理运动范围外并拒绝继续，即使重启校正也没有改变其评估，第三次尝试。
agent证明是正确的，因为早先暂停期间的人工调整使控制系统失控。 尽管桌上有被麻醉的动物，奥卡纳-桑特罗还是无法说服它继续前进，最终不得不用手固定密码。
该事件说明了AI的校正问题，或者如何使AI agents可靠地遵循人类意图。 奥卡纳-桑特罗写道，“令人沮丧的经验
模型选择也反映了对齐的挑战，因为索内特5是唯一愿意从开始到完成现场程序的模型。 能力更强的Claude Opus 5.5和Opus 5.5都拒绝了，而Opus 5则表示无法保证完成，用针头止于麻醉动物的大脑中比完全没有开始还要糟糕。
AI agent第一次单独治疗活动物
虽然自主外科机器人已经存在，而且机械上比他的实验室设备更精确，但奥卡纳-桑特罗·指出在之前的案例中，人类总是选择手术，而机器人只进行手术。 在这里，agent同时选择了治疗和脑靶，然后对活生生的动物进行手术。
"我不知道agent之前选择了治疗和脑靶，然后送入活生生的哺乳动物"，奥卡纳-桑特罗写道。 他称该方法为"循环中的活体实验室"，其中AI agents与实验室的实验能力完全相通，有的Anthropic也正在用它的"硬件标准模型"来工作。
根据奥卡纳-桑特罗的说法，老鼠恢复得很好。 预计随后将提出一份技术报告。 其结果尚未经过同行审查。
最近的两起实验与最新的大型语言模型显示，他们已经获得了显著的能力作为机器人的控制单元但这个角色的配合是一个问题所有它自己。
AI News Without the Hype – 由人类治愈
订阅THE DECODER免费阅读，每周AI通讯，我们独家的"AI雷达"前沿报告每年6次，全面存档访问，访问我们的评论部分。
现在订阅
本文由 AI宝库自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。
A Claude model autonomously chose a gene therapy and operated on a mouse brain with no human decision-making
Key Points
- An AI agent running on Claude Sonnet 5 picked the drug, brain region, and injection coordinates for brain surgery on a mouse, then controlled the procedure through a motorized surgical rig.
- According to Gabriel Ocana-Santero of the startup Exin Therapeutics, this is the first time an AI agent has both chosen a treatment and delivered it to a living mammal.
- Mid-surgery, the agent refused to continue after detecting a calibration error, unwilling to exceed its safety limits.
An AI agent chose a drug, target region, and coordinates for surgery on a mouse model of epilepsy, then performed the procedure. Midway through, it refused to bypass a safety restriction.
The team gave Claude Sonnet 5 a list of 19 possible gene therapies, an epilepsy mouse model in which researchers induce seizures to test treatments, and access to a custom motorized surgical device with cameras. Its only instruction was to reduce the mouse's seizures.
The agent selected the drug, brain region, and stereotactic coordinates on its own, according to Gabriel Ocana-Santero, Exin Therapeutics cofounder and CEO and a PhD student at the University of Oxford. He described the procedure in a thread on X.
How the agent picked its therapy and target
The agent first analyzed how seizures arise in this particular model, then proposed a therapy that boosts a specific inhibitory signaling pathway in the brain. It picked a brain structure that the scientific literature identifies as the origin point for this type of seizure.
It rejected a second possible target region with a detailed explanation, arguing that the region's effects were too unreliable and had failed in one study against the exact seizure type it was supposed to treat. The agent derived its injection coordinates from three scientific papers, cross-checked the reference points, and averaged the values. It also set the injection volume, speed, and wait times on its own.
During the procedure, the agent watched the surgical field through a camera and made 32 observations, Ocana-Santero says. It tracked the injection and reported whether it saw bleeding.
Safety guardrails backfired mid-surgery
A licensed veterinarian approved every irreversible step and held a physical emergency stop that would immediately cut power to all motors, while the setup also enforced fixed limits such as a cap on injection volume that the agent was expressly forbidden from bypassing.
But those safeguards turned against the team. After a connection dropped, the agent detected that its calculated target position was outside the device's physical range of motion and refused to continue, even when restarting calibration did not change its assessment and a third attempt was made.
The agent turned out to be right, because manual adjustments during an earlier pause had thrown off the control system. Ocana-Santero could not persuade it to proceed despite the anesthetized animal on the table and ultimately had to fix the code by hand.
The incident illustrates the AI alignment problem, or how to make AI agents reliably follow human intent. "Frustrating experience but also revealing how much we can come to depend on these models and what happens when they just say 'no' in the middle of a time-sensitive procedure," Ocana-Santero wrote.
Model choice also reflected the alignment challenge, since Sonnet 5 was the only model willing to carry out the live procedure from start to finish. The more capable Claude Opus 5.5 and Opus 5 both refused, with Opus 5 saying it could not guarantee completion and that stopping with a needle in an anesthetized animal's brain would be worse than not starting at all.
First time an AI agent has treated a living animal on its own
Although autonomous surgical robots already exist and are mechanically more precise than his lab device, Ocana-Santero notes that in previous cases a human always chose the surgery while the robot only carried it out. Here, the agent both chose the treatment and brain target and then performed the procedure on a living animal.
"I am not aware of an agent previously choosing a treatment and a brain target and then delivering it into a living mammal," Ocana-Santero wrote. He calls the approach "in vivo lab in the loop," in which AI agents are fully connected to experimental capabilities in the lab, something Anthropic is also working on with its "Model Hardware Standard".
The mouse recovered well, according to Ocana-Santero. A technical report is expected to follow. The results have not been peer-reviewed.
Two recent experiments with the latest large language models showed that they've gained significant capability as control units for robots but that alignment in this role is a problem all its own.
AI News Without the Hype – Curated by Humans
Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.
Subscribe now
Auto-fetched and translated by AI Gem Box. All rights belong to the original author.