GPT-5.6 Sol Autonomously Runs Quantum Computing Experiments at MIT

OpenAI said GPT-5.6 Sol, harnessed to Codex, helped run quantum computing experiments. Beatriz Yankelevich, a graduate student in MIT's Engineering Quantum Systems Group, used the model to explore whether AI could streamline her experimental workflow on superconducting qubits. Preparing and running qubit experiments can take months and require hundreds to thousands of preliminary measurements. Once a superconducting qubit chip has been fabricated, packaged, and cooled, researchers interact with it entirely through software, making Yankelevich's experiments a natural testbed for AI agents. The MIT group studies superconducting qubits, which are cooled to near absolute zero inside specialized devices called dilution refrigerators. These qubits perform operations quickly, are precisely controlled using microwave signals, and can be made using familiar manufacturing techniques and arranged on a chip. Superconducting qubits are often called artificial atoms because, like atoms, they can only occupy specific energy levels. Microwave pulses move qubits between these levels and probe their quantum state. Researchers design and calibrate the pulse sequences sent to the chip, then digitize and analyse the returning signals. These measurements reveal each qubit's resonance frequencies, which allows researchers to accurately control the qubit; how long the qubit retains quantum information; and the settings needed to perform computations. Calibrating qubits requires a series of interdependent measurements, with each result shaping what happens next. Qubit properties can occasionally drift, and unexpected physical behavior can cause inconsistent results. Connecting Codex to the lab software that coordinates experiments allowed it to run measurements, analyze the results, and decide what to try next. Yankelevich tested GPT-5.6 Sol's ability to run measurements on an uncalibrated six-qubit chip, one of a standard type that EQuS routinely uses to benchmark its fabrication process. She provided Codex with measurement-specific skills. Yankelevich found that GPT-5.6 Sol could often complete routine measurement workflows autonomously, saving her significant amounts of time and allowing experiments to run without constant supervision. This freed her to spend more time on analyzing results, designing experiments, and planning out the next steps in her research. The combination of software control, repeated measurements, and adaptive decision-making makes qubit calibration a compelling use case for AI agents.