Research #Anthropic #AI agents Oct 19, 2026 · Originally published Oct 16

Working in a closed loop with an evaluator, Claude Mythos 5 designs quantum circuits that beat the best published ones on qubits and gates in all eight tasks, one key step about 12x cheaper

Given a plain-language spec and an automatic scoring evaluator, the model iterated on designs for tens of hours on its own. Quantum is far from most products, but the spec-plus-evaluator loop is directly reusable.

Primary source Anthropic Research · anthropic.com Read the original ↗

// Key points

Claude got plain-language specs for eight quantum circuits across chemistry, optimization, quantum simulation, number theory and numerical computing; an evaluator checked correctness and scored qubits times gates.
Claude Mythos 5 proposed designs, received scores and improved them in a loop with no human input between rounds; in all eight tasks it found designs with fewer qubits and fewer gates than the best published algorithms, some by an order of magnitude or more.
On elliptic-curve point addition, Claude worked for 53 hours with only the initial brief and occasional prompts to think more broadly, arriving at a new approach to modular inversion.
Another result makes the costliest step of a leading quantum optimization algorithm about 12x cheaper; the full paper is on arXiv.

Builder's takeWhat interests me isn't quantum but the method: once a task can be checked automatically and given an objective score, a model can run on its own for tens of hours. In a product, pick out problems like that, such as retrieval recall in AI Cloud Drive or prompt scores on a fixed question set, write the evaluator first and let an agent iterate; it beats a human babysitting the tuning.

// Background · from #Anthropic

Full timeline →