Claude Solves Nine-Loop Calculation in Planar N=4 Super Yang-Mills
The striking part is the cost: a calculation that once took specialist teams years now ran for a few thousand dollars of compute from a single unsupervised model run. Theoretical physicists and AI researchers should watch this as a benchmark for scientific reasoning workloads, and verify replication details on Anthropic's blog. Kevin Weil's amplification also signals how quickly US labs are positioning frontier models as physics research tools.
Anthropic reports that Claude, given a single prompt describing a nine-loop scattering amplitude problem, ran largely unsupervised for days and solved it in planar N=4 super-Yang-Mills.
The previous record of eight loops was set by SLAC physicist Lance Dixon and collaborators in this simplified testing-ground model.
Most physics calculations stop at two or three loops, as each added loop increases precision but raises computation exponentially.
Dixon independently verified the result, which was produced with an academic-scale compute budget costing a few thousand dollars.
The work appeared on Anthropic's Science Blog, with physicist von Hippel documenting the experience.
Nine loop calculations in N=4 Super Yang-Mills! Lance Dixon's 8-loop calculation was mind boggling when he did it. I calculated a lot of Feynman diagrams in grad school and this is 🤯 Will be amazing to see where AI will take high energy physics in the coming 12 months. Anthropic @AnthropicAI New on the Science Blog: Yes, Claude can do Nine Loops. Theoretical physicists predict how particles behave using formulas called scattering amplitudes. These are notoriously hard to compute, so researchers work with layers of increasingly fine corrections called “loops”—each added loop makes the answer more precise but takes exponentially more computation. Most calculations stop at two or three loops. Eight loops was the previous record in a simplified model physicists use as a testing ground (planar N=4 super-Yang-Mills), set by SLAC's Lance Dixon and collaborators. Last month, physicist and science writer @4gravitons issued a challenge: could an AI push past eight loops in this model, using only the compute budget an academic could reasonably access? Given a single prompt describing the nine-loop problem, Claude ran largely unsupervised for days in Claude Science and solved it using methods developed by Dixon and his colleagues, at a total cost of a few thousand dollars. Dixon independently verified the result, and von Hippel wrote about the experience for our blog. Read more: anthropic.com/research/yes-c… 🔗 View Quoted Tweet📊 53 ⚡
This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Claude, Anthropic.
Source attribution: curated from Kevin Weil (@kevinweil). Cross-source corroboration: 11 independent sources have covered this development (including Anthropic, IT之家, rohanpaul_ai), confirming industry-wide signal strength.
