- Last night an AI agent performed brain surgery on a mouse. We gave it 19 gene therapy vectors in a spreadsheet, a mouse model of epilepsy, access to a motorize surgery rig with cameras and one goal: reduce seizures. It picked the drug. It picked the brain region. It derived the coordinates from three papers. Then it drove the stereotaxic arms into the brain and injected 250 nanolitres while watching the entry site through the rig camera for bleeding. A licensed vet gated every irreversible step and held a physical kill switch to stop the AI agent. Thread on what it decided, what it saw, and the moment it refused to let me override it. [Writing this on the spot out of excitement, but I've been 18hrs in front of my laptop coding and coordinating this, so keeping it brief and descriptive, more cohesive thoughts on this soon...]
For the lab-in-the-loop aficionados, this is a custom-made motorized surgery rig we built on arduino. So to connect it to our agents we exposed the camera and motor capabilities through our own customized solutions (more detail soon on the technical report). We are still tryingAgent reasoning On the scientific rational, the agent worked through the mechanism that drives seizures in this model, then proposed a therapy that increases GABA signalling, the brain's primary inhibitory neurotransmitter, under a promoter that restricts expression to GABAergicThe agent was not flying blind. The rig has a camera on the surgical field and the agent pulls frames whenever it wants. It did 32 observations this session, some examples: Watching our surgeon do the craniotomy, which the agent is not allowed to do yet for safety reasons, itSafety measures and concerns We implemented a series of safety measures: human gates on everything irreversible; fixed validators (e.g., limits on volume injected); hash-bound approval and a physical e-stop (aka "AI kill switch") cutting power to every motor, held by our vetModels of choice Opus 5.5 refused immediately when detected bio. Opus 5 ran the entire dry run end to end on water and graph paper, then stopped at the start of the live surgery. Under this statement: "The block isn't the rig and isn't the inputs. It's me. My own output wasEARLY conclusions Autonomous surgical robots exist and they are better at the mechanics than our bench rig tbh. But in every one of them, a human decided what operation to perform, and the robot executed it. Nobody told this agent what to give or where to put it. It got a00:00wow didn't expect this to go so viral hahah couple papers on other cool stuff we do: arxiv.org/abs/2610.11222 & arxiv.org/abs/2610.09643 website: exintherapeutics.com my cofounder and partner in crime: @markotvrdic If you think this is cool, wait for what's coming...
Last night an AI agent performed brain surgery on a mouse
Related Stories
Airlock: a veto window for your POT, built on Portaldot's Proxy pallet
Dev.to
2 days ago
An agent payment security checklist, from the payout address to the signer
Dev.to
2 days ago
AI agent payments usually get the flow right and the trust wrong
Dev.to
3 days ago
How a $5.3B Binance Hot-Wallet Hack Worked: EIP-7702, 50 Signatures and a 37-Minute Race
Dev.to
3 days ago
SpendMemory: A payment review that remembers why
Dev.to
4 days ago