Yes, Claude can do Nine Loops
Anthropic's Claude tackled a nine-loop N=4 super Yang-Mills calculation posed as a hard physics test.
In an Anthropic research guest post, physicist Matt von Hippel describes a challenge for AI labs: using academic-scale computing, push scattering-amplitude calculations to N=4 super Yang-Mills at nine loops or N=8 supergravity at seven loops. He says Anthropic took the nine-loop N=4 super Yang-Mills problem, a toy model used because supersymmetry makes it easier than real-world particle theories. The essay says the challenge was beaten about a month later, and the title states that Claude can do the nine-loop calculation.
- The challenge sought nine-loop N=4 super Yang-Mills on academic-scale compute.
- Anthropic chose that target rather than seven-loop N=8 supergravity.
- More loops make scattering-amplitude predictions more precise and far costlier.
- The post presents Claude as meeting that computational physics challenge.
From the original article
15 min read at anthropic.com
In this guest post, physicist and science writer Matt von Hippel shares what happened when he issued a challenge to AI companies regarding a problem in his former subfield of theoretical physics. It’s not often that you issue a challenge, only to see it beaten a month later. But we’re living in unusual times.
By tzury · anthropic.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.