Claude (Fable 5.1 in Claude Science) computes the nine-loop six-gluon amplitude in planar N=4 super-Yang-Mills, answering a physicist’s public challenge
Result confirmed
Importance: major (4 of 5)The takeaway
On Sept 25, 2026 Anthropic published a guest post by physicist-turned-writer Matt von Hippel.
Status
- Claim
Result confirmed
- Our reporting
- High confidence
- Verification
- Expert-checked
- Importance
- Major (4 of 5)
- Last verified
- 7 October 2026
Your AI and this story
- GPT-6.2 Astra117 days after its cutoff
- Claude Opus 5.587 days after its cutoff
- Gemini 4 Hydrogen178 days after its cutoff
- Grok 4.7117 days after its cutoff
None of these four assistants can know about it. The closest, Claude Opus 5.5, stops 87 days before it.
Key facts
- Challenge: von Hippel’s 4gravitons post of Aug 7, 2026 (‘It only counts when AI gets to my field’) asked for N=8 supergravity at seven loops or N=4 SYM at nine loops on academic-scale compute; Anthropic reached out at the end of August
- Setup: Claude Fable 5.1 in Claude Science; initial prompt ‘The problem is to compute the Six-particle (hexagon) amplitude in planar N=4 SYM at nine loops’, then instructions like ‘Keep working on this until I tell you to stop. Give me updates every 4-6 hours’
- Two routes: (1) bootstrap the nine-loop three-point form factor and map it to the amplitude via antipodal duality (the method Dixon used for eight loops, arXiv 2308.08199); (2) a direct bootstrap of the symbol in the space of hexagon functions. The two agree on every coefficient compared
- Cost: about $1,000–2,000 end-user price per approach, mostly Claude usage; the SymPy bootstrap cost ~$100 of compute (96 CPUs for about a week)
- Verification: checked with Lance Dixon (SLAC), who holds the six-, seven- and eight-loop results; the form factor is certified over the rationals at three 31-bit primes, the amplitude computed modulo two primes (99.62% of nonzero symbol coordinates reconstruct to certified rationals)
- Data released on Mishra-Sharma’s ‘Cosmic9’ page and Zenodo (symbol as 424 quintuple coproducts over a 5,431-dimensional weight-13 hexagon symbol space); the programs are not distributed
- Priority: Song He’s group (Chinese Academy of Sciences, Beijing) had independently obtained ‘the majority of the result’ using GPT-6-based AI assistance; the human groups will publish the physics analysis
- Von Hippel’s verdict: Claude ‘used known methods, with a bit more compute than people had tried to use before’, not new methods; but ‘this is a real frontier calculation’ done essentially autonomously, and ‘there is more low-hanging fruit out there than you’d expect’
What happened
Scattering amplitudes are usually computed to two or three loops. The planar N=4 super-Yang-Mills “toy model” has been pushed furthest with the amplitude bootstrap. Dixon and collaborators reached eight loops indirectly through a form factor. Anthropic’s physicists asked Claude which of von Hippel’s two challenges it was most likely to solve, then let the Claude Science harness run for days with minimal oversight. Von Hippel says either route would have cost an end user about one or two thousand dollars.
Why it matters
It is a frontier-level computation in theoretical physics done almost autonomously by an AI agent on a modest budget. As the challenger notes, it used known methods rather than new ones, and humans (Song He’s group, with GPT-6 help) were close behind. It suggests that much “compute-limited” science is really limited by labour and engineering.
Sources
6 sources from 5 sites. Numbers match the chips in the text.
6 sources: 5 primary, 1 reaction
Primary
- Zenodo 22800071: The Symbols of Six-Gluon MHV Amplitudes through Nine Loops (Song He, Jirong Jing, Xiang Li; ITP-CAS/UCAS; Sept 17, 2026)zenodo.org, code
- Zenodo 22949278: Nine-loop six-gluon MHV amplitude in planar N=4 SYM, large data files (author: Claude (Anthropic), Sept 25, 2026, CC BY 4.0)zenodo.org, code
- Anthropic (guest post by Matt von Hippel): Yes, Claude can do nine loopsanthropic.com, official
- Cosmic9: nine-loop six-point amplitudes computed by Claude (data page)smsharma.io, code
- arXiv 2308.08199: eight-loop amplitude via form factor and antipodal duality (Dixon et al.)arxiv.org, paper
Reactions
- 4gravitons: It only counts when AI gets to my field (the challenge, Aug 7, 2026)4gravitons.com, discussion
Changes
- Science block: kind: other (not a long-open problem; listed with other AI science results, not in the open-problems count)
- Added the Song He group’s own dataset (Zenodo 22800071, Sept 17: symbols through nine loops, by He, Jing and Li); their paper and the Dixon/He analysis are still not on arXiv
- Added the Zenodo data record (author field ‘Claude (Anthropic)’); the Song He group paper is still not on arXiv
- Filed (found in the lab-blog check; not previously covered)