Source
How GPT-5.6 Sol helps run quantum computing experiments
MIT researcher Beatriz Yankelevich used GPT-5.6 Sol and Codex to automate routine measurements and calibration of superconducting quantum computing chips.
Why it matters
Automating repetitive measurements saves researchers significant time and allows experiments to run overnight without constant supervision.
The big picture
While previous coverage noted Codex uses GPT-5.6 Sol for writing GPU kernels, this demonstrates its application in physical laboratory automation.
The details
Superconducting qubits are cooled to near absolute zero inside dilution refrigerators. GPT-5.6 Sol identified qubit transition frequencies and calibrated control and read pulses. Yankelevich employs agents across measurement, theory, and chip design.
Show entities and relationshipsHide entities and relationships
In this article
Technologies
Products
Companies
People
Organizations
Key connections
Beatriz Yankelevich works at MIT’s Engineering Quantum Systems Group (EQuS)
a graduate student in MIT’s Engineering Quantum Systems Group (EQuS)
Beatriz Yankelevich uses GPT-5.6 Sol
used GPT‑5.6 Sol, harnessed to Codex, to explore whether AI could streamline her experimental workflow
Beatriz Yankelevich uses Codex
provided Codex with measurement-specific skills
GPT-5.6 Sol is related to Codex
GPT‑5.6 Sol, harnessed to Codex
GPT-5.6 Sol is related to AI Agents
making Yankelevich’s experiments a natural testbed for AI agents
Codex agents can help researchers make steady progress
Get the weekly recap
The stories like this one, picked and explained — once a week, straight to your inbox.