Skip to content
Anthropic Research·Indexed by this site · Originally publishedSelectedAttention32

Anthropic uses Claude to design more efficient quantum circuits

Designing more efficient quantum circuits with Claude

AI summary

Anthropic says Claude Mythos 5 designed quantum circuits largely autonomously in an automated evaluation loop, outperforming the best published approaches on eight computational primitives spanning chemistry, optimization, quantum simulation, and number theory, with some improvements reaching an order of magnitude. The researchers gave only a natural-language description, and an evaluation program verified circuit correctness and scored circuits by qubit count multiplied by gate count; Claude iterated on that basis without human intervention. On the elliptic-curve point-addition task, after a 53-hour run Claude produced what Anthropic calls the first reversible divsteps implementation that does not store branch information, and one of its designs used 12% more qubits than the previous smallest design but reduced gate count by 17 times. It also cut the gate count of the most expensive Reed–Solomon decoder in DQI to 1/12 of Google's earlier construction. The authors also note that Claude was initially conservative and favored existing methods, and the team mitigated this by requiring parallel proposals of multiple approaches and occasionally prompting it to broaden its search.

Why it was selected

Anthropic uses an automated evaluation loop to let Claude autonomously improve quantum circuit designs, outperforming published approaches on all eight tasks, and the closed-loop approach can transfer to other scoreable tasks.

Related papers
Read originalanthropic.com