Anthropic Physics Team Computed Nine-Loop Amplitude
Physicists used the Claude AI to solve a complex six-particle scattering amplitude calculation.
Updated on Sept. 25, 2026 in Physics
Live Poll
Do you believe the use of AI for complex scientific research will improve future discovery?
Anthropic researchers have completed a nine-loop calculation for six-particle scattering in planar N=4 super Yang-Mills theory. The AI-driven computation surpassed the previous record established in 2023.
Why it matters
This breakthrough demonstrates the utility of large language models in solving advanced symbolic mathematical problems that previously required years of manual work. The successful experiment answers a high-profile public challenge to apply AI to complex theoretical physics.
The project involved six-particle scattering amplitudes within planar N=4 super Yang-Mills theory. The resulting data files exceeded 100 megabytes in size, produced through a direct bootstrap of hexagon functions.
The players
Liam Fitzpatrick
He is an Anthropic physicist who led the successful computation of the nine-loop scattering amplitude.
Siddharth Mishra-Sharma
He is an Anthropic physicist who collaborated on the utilization of Claude to solve the scattering amplitude problem.
Lance Dixon
He is a physicist who served as the independent verifier for the computation results.
Matt von Hippel
He is a researcher who issued the public challenge in August 2026 that initiated this computational project.
The details
Physicists Liam Fitzpatrick and Siddharth Mishra-Sharma utilized the Fable 5.1 model on the Claude Science platform to complete the calculation. The AI operated largely unsupervised for several days, using both the bootstrap of hexagon functions and antipodal duality to derive the results, which were subsequently verified by physicist Lance Dixon.
Timeline
August 7, 2026: Matt von Hippel issued the open AI challenge.
Late August or early September 2026: The nine-loop result calculation was completed.
September 16, 2026: The data files were released publicly on Zenodo.
September 25, 2026: Anthropic announced the nine-loop calculation results.
Deeper Dive
This project follows a pattern set by the 2023 eight-loop scattering amplitude calculation by successfully increasing the complexity of the loop order using automated methods. The results extend the reach of symbolic computation in theoretical physics.
The success of this AI-driven approach suggests that high-complexity symbolic math problems could eventually be solved at a fraction of their current cost. Future iterations may allow researchers to automate repetitive theoretical derivations, accelerating progress in fundamental physics.
The takeaway
This achievement highlights the growing potential for AI models to serve as advanced tools for tackling complex theoretical calculations. By automating these processes, scientists can potentially solve problems that were previously limited by human computational throughput.
Further reading
Learn more about the latest research in /science/physics/.
Source note: This article includes information reported by Crypto Briefing.
Live Poll
Do you believe the use of AI for complex scientific research will improve future discovery?
