How GPT‑5.6 Sol helps run quantum computing experiments
Connecting GPT‑5.6 Sol to laboratory software to run and refine routine measurements on quantum chips freed Beatriz Yankelevich to focus on experiment design and data analysis.
Quantum computing is an emerging technology that uses the unique properties of quantum mechanics to process information. It could one day better simulate complex materials and molecules. Unlike conventional processors, quantum processors are built with quantum bits, or qubits. Preparing and running qubit experiments can take months and require hundreds to thousands of preliminary measurements—work that AI is poised to help with.
Beatriz Yankelevich, a graduate student in MIT’s Engineering Quantum Systems Group (EQuS), used GPT‑5.6 Sol, harnessed to Codex, to explore whether AI could streamline her experimental workflow. 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.
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. Connecting Codex to the lab software that coordinates experiments allowed it to run measurements, analyze the results, and decide what to try next. 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.
Coordinating interdependent measurements
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. Experienced researchers can recognize these changes and adapt when they occur. This combination of software control, repeated measurements, and adaptive decision-making also makes qubit calibration a compelling use case for AI agents.
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 explaining how to run and evaluate each experiment. Using these skills and the chip’s design targets, GPT‑5.6 Sol chose measurement parameters, operated the hardware, analyzed the resulting data, and then either refined the measurement or saved the result for use in the next measurement.
When the signals were clear, Codex completed a standard sequence of measurements with little researcher intervention. It identified the qubit’s transition frequencies, calibrated the pulses used to control and read it, and determined how long the qubit retained quantum information.
GPT‑5.6 Sol had more difficulty when experimental signals were weak or noisy. In those cases, it took longer to find suitable measurement parameters and sometimes needed guidance from an experienced researcher. The results suggest that current agents can handle clearly defined experimental workflows, but interpreting ambiguous physical results remains a challenge.
EQuS fabricates many of these standard chips, each of which can take a researcher several days to characterize. The group now regularly uses agents to handle routine measurements, freeing researchers to focus on other work.
“I can have agents running measurements for many hours overnight or while I’m working in the cleanroom,” Yankelevich said. “I can check in from my phone, see what they’ve done, and steer them if something needs fixing or if I want to explore a different direction.”
Working alongside researchers
The immediate advantage is that Codex agents can help researchers make steady progress on experimental analysis and measurements without constant supervision. Experienced researchers may still be able to identify the best calibration settings faster than current AI models. But by saving time previously spent on monitoring every step of the calibration process, researchers can focus on other work.
Routine chip characterization follows a relatively well-defined workflow. For novel experiments, Yankelevich assigns Codex agents narrower experimental goals while drawing more heavily on their ability to write, modify, and test new code for control, analysis, and simulation. Connecting agents directly to the lab lets the group revise code, test it against real measurements, and complete longer stretches of work autonomously.
“I’ve built infrastructure to guide agents through several parts of my work—measurement, theory, and chip design—and now it’s really starting to pay off,” Yankelevich said. “I can have multiple agents working on different problems at once, and I spend most of my time on higher-level work—interpreting results, devising experiments, planning next steps for the agents, reading, and writing.”
- 2026
- Codex
Facts Only
* GPT-5.6 Sol was used to connect to laboratory software for running and refining routine measurements on quantum chips.
* Beatriz Yankelevich, a graduate student in MIT’s Engineering Quantum Systems Group (EQuS), used the system harnessed to Codex.
* The research involves superconducting qubits studied by the EQuS group.
* Superconducting qubits are cooled to near absolute zero inside dilution refrigerators and controlled by microwave signals.
* Qubit calibration requires a series of interdependent measurements.
* GPT-5.6 Sol autonomously chose measurement parameters, operated hardware, analyzed data, and refined measurements on an uncalibrated six-qubit chip.
* The AI successfully identified qubit transition frequencies, calibrated control pulses, and determined quantum information retention time during a standard measurement sequence.
* The system encountered difficulty when experimental signals were weak or noisy, requiring guidance from a researcher.
* Researchers are using agents to handle routine measurements, allowing them to focus on experiment design and data analysis.
Executive Summary
GPT-5.6 Sol was connected to laboratory software to manage and refine routine measurements on quantum chips, allowing Beatriz Yankelevich to focus on experiment design and data analysis. This capability was demonstrated in the context of superconducting qubits, which are used by the MIT Engineering Quantum Systems Group (EQuS). The system allowed AI agents to autonomously run measurement workflows, analyze results, and decide on subsequent steps, significantly reducing the need for constant researcher supervision during routine tasks.
The process of qubit calibration involves interdependent measurements where each result influences the next step, a task that benefits from adaptive decision-making by AI. In one test, GPT-5.6 Sol ran measurements on an uncalibrated six-qubit chip by autonomously selecting measurement parameters, operating the hardware, analyzing data, and refining measurements. However, the system faced difficulties when experimental signals were weak or noisy, indicating a current limitation in interpreting ambiguous physical results.
The immediate advantage is that AI agents can handle routine characterization, freeing up researchers to concentrate on higher-level tasks such as designing experiments, planning research directions, and interpreting complex results. For novel experiments, the agents can be guided to perform specific experimental goals while leveraging their coding and simulation abilities for broader tasks.
Full Take
The narrative demonstrates the potential for autonomous agents to bridge the gap between raw quantum measurement and high-level scientific interpretation, moving beyond mere execution toward adaptive experimentation. The core pattern observed is the value placed on workflow automation to alleviate the cognitive load associated with iterative physical calibration. The transition from a manually supervised calibration process to an agent-guided one suggests a shift in the boundary of what constitutes "expert" knowledge—from meticulous, moment-to-moment parameter adjustment to setting high-level strategic goals and verifying complex outcomes.
The limitation encountered when signals are weak highlights a critical vulnerability: AI excels at executing clearly defined workflows but struggles with the nuanced interpretation of ambiguous physical reality, which is essential in cutting-edge physics. This implies that current AI agents function best as powerful execution tools within established frameworks rather than fully autonomous scientific intuition providers. The broader implication is whether delegation of routine measurement and calibration risks deskilling the human expert in recognizing subtle, emergent physical behaviors that necessitate new experimental paradigms.
The system’s ability to handle intertwined tasks—measurement, theory, chip design, and code modification simultaneously—suggests a future where AI acts not merely as an assistant but as an integrated research partner capable of navigating multi-modal scientific environments. The challenge then becomes structuring the human role to effectively supervise this layered autonomy, ensuring that the focus remains on defining novel, unconstrained problems rather than supervising known procedural tasks.
BRIDGE QUESTIONS:
What specific forms of guidance most effectively bridge the gap when experimental signals are ambiguous? How should the definition of "routine workflow" evolve as AI autonomy increases in physics? What necessary human oversight mechanisms must be established to prevent the loss of expert intuition during autonomous calibration processes?
Sentinel — Human
The text reads as a highly technical news report or research summary focused on the practical application of AI agents in quantum computing experiments, supported by direct statements from the involved researcher.