How GPT-5.6 Sol helps run quantum computing experiments | OpenAISkip to main contentResearchProductsBusinessDevelopersCompanyFoundation(opens in a new window)Log inTry ChatGPT(opens in a new window)ResearchProductsBusinessDevelopersCompanyFoundation(opens in a new window)Try ChatGPT(opens in a new window)LoginOpenAISeptember 8, 2026Applied AIHow GPT‑5.6 Sol helps run quantum computing experimentsConnecting 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.Read the technical case study(opens in a new window)Loading…ShareQuantum 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.A packaged qubit chip (left) sits inside an open dilution refrigerator (right). CREDIT: EQuS groupCoordinating interdependent measurementsSuperconducting 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.A set of calibration measurements for one qubit, completed autonomously by GPT‑5.6 Sol. CREDIT: EQuS groupA set of calibration measurements for one qubit, completed autonomously by GPT‑5.6 Sol. CREDIT: EQuS groupA set of calibration measurements for one qubit, completed autonomously by GPT‑5.6 Sol. CREDIT: EQuS groupGPT‑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.”An excerpted GPT‑5.6 Sol chain-of-thought from a calibration run. CREDIT: EQuS groupWorking alongside researchersThe 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.”2026CodexAuthorOpenAIKeep readingView allThe builder’s guide to GPT‑5.6Applied AIAug 13, 2026How GPT-5 helped immunologist Derya Unutmaz solve a 3-year-old mysteryApplied AIJun 23, 2026Using AI to help physicians diagnose rare genetic diseases affecting childrenApplied AIJun 18, 2026ResearchResearch IndexResearch OverviewEconomic ResearchLatest AdvancementsGPT-6GPT-5.6GPT-5.5GPT-5.4SafetySafety ApproachDeployment Safety(opens in a new window)Security & PrivacyTrust & TransparencyProductsChatGPT(opens in a new window)ChatGPT Business(opens in a new window)ChatGPT Enterprise(opens in a new window)ChatGPT for Education(opens in a new window)CodexRelease NotesAPI PlatformOverviewAPI Log In(opens in a new window)Docs(opens in a new window)BusinessOverviewSolutionsResourcesCustomer StoriesPartner NetworkContact SalesDevelopersApps SDK(opens in a new window)Open ModelsDocs(opens in a new window)Resources(opens in a new window)Developer Forum(opens in a new window)CompanyAbout UsOur CharterCareersNewsSupportHelp Center(opens in a new window)MoreStoriesAcademySupply Co.LivestreamsPodcastRSSTerms & PoliciesTerms of UsePrivacy PolicyOther Policies (opens in a new window)(opens in a new window)(opens in a new window)(opens in a new window)(opens in a new window)(opens in a new window)(opens in a new window)OpenAI © 2015–2026Your privacy choicesEnglishUnited States

GPT-5.6 Sol, through its implementation in Codex, assists researchers in streamlining the workflow for quantum computing experiments by connecting directly to laboratory software to execute and refine routine measurements on quantum chips. This capability is particularly relevant because preparing and running qubit experiments often necessitates months of preliminary measurements and hundreds or thousands of such tests. The research context involves superconducting qubits, which are studied by the group led by Beatriz Yankelevich at MIT’s Engineering Quantum Systems Group (EQuS), operating within dilution refrigerators to maintain near absolute zero temperatures, and are controlled by microwave signals.

The complexity arises because qubit calibration requires a sequence of interdependent measurements; the results from each measurement inform subsequent steps, and physical properties can drift or exhibit unexpected behavior, complicating the process for human researchers who must constantly recognize changes and adapt. This interdependence, combined with software control and repeated measurements, presents a compelling area for the application of AI agents.

Yankelevich explored using GPT-5.6 Sol to manage this complex calibration process. She tasked Codex with running measurements on an uncalibrated six-qubit chip, providing it with measurement-specific skills detailing how to execute and evaluate each experimental step based on the chip’s design targets. The agent autonomously selected measurement parameters, operated the necessary hardware, analyzed the resulting data, and subsequently either refined the measurement or saved the outcome for subsequent tests. In clear signal conditions, Codex successfully completed a standard sequence of measurements, identifying transition frequencies, calibrating control pulses, and determining quantum information retention times with minimal direct intervention from the researcher.

While this autonomous execution offers a significant advantage by handling routine measurement workflows without constant supervision, the system demonstrated limitations when experimental signals were weak or noisy, often requiring guidance from an experienced researcher to select appropriate parameters. This suggests that while current AI agents excel at executing clearly defined workflows, interpreting ambiguous physical results remains a challenge. Nevertheless, the immediate benefit is allowing agents to handle lengthy tasks, such as running measurements overnight in the cleanroom, which frees up researchers to dedicate their time to higher-level activities like designing experiments, analyzing complex results, and planning future research directions. Furthermore, when dealing with novel experiments, researchers can assign agents narrower goals while leveraging the AI's coding and simulation abilities to modify and test new control sequences against real measurements. This integration allows for multiple agents to work on different problems concurrently, enabling researchers to focus predominantly on interpreting results and devising strategic next steps.