Understand this story
On October 17, 2026, Anthropic published a study: when given only a pure natural-language specification and an automated evaluator, Mythos 5 essentially without human intervention repeatedly submitted and improved quantum circuit designs in a closed loop, finding circuits that use fewer qubits and gates than the best previously published solutions, with some improvements reaching an order of magnitude. The elliptic-curve modular inversion design came from a single 53-hour continuous run, in which the model derived a reversible divsteps implementation that requires no storage of branch information and formally verified it with Lean; another effort reduced the gate count of the Reed-Solomon decoding step, the most expensive step in DQI, to about 1/12 of a construction previously made by Google. Anthropic also noted that the model was initially conservative and tended to follow known methods, which needed to be mitigated by requiring parallel exploration of multiple approaches and occasionally prompting it to broaden its search. Subsequent reports said the research came from the STEM Fellows program and gave differing formulations, such as a 17-fold reduction in gate count for the divsteps task.
AI-generated from public reports
Developments
1 confirmed developments
Anthropic publishes research on Mythos 5 autonomously designing quantum circuits
Source:Anthropic Research
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 18
36Kr · AISelected
Anthropic says Mythos 5 autonomously designed quantum circuits, surpassing human optimal solutions in 53 hours
Anthropic announced a study in which Mythos 5, given only natural language task descriptions, fully autonomously closed-loop designed 8 basic quantum circuits within 53 hours, all surpassing the best publicly published human designs. In the divsteps task in number theory and cryptography, it autonomously derived a new algebraic identity and completed formalization in Lean, reducing the number of quantum gates by 17 times while increasing qubits by only 12%; in the DQI decoding task, it switched to the Berlekamp-Massey decoding method and precisely calculated storage requirements, reducing gate count by 12 times compared with the original architecture. The research comes from Anthropic's STEM Fellows project, and the text also mentions that FeMoco simulation gate count dropped from the 50 trillion estimated by humans in 2017 to 340 million over 8 years.
Oct 17
Rohan Paul
Claude Mythos 5 designs elliptic curve quantum circuits with 17x fewer gates
In Anthropic's STEM Fellows Program, Harvard physics researcher Andi Gu had Claude Mythos 5 design quantum circuits, surpassing human design records on most of 8 tasks. In one elliptic curve quantum circuit, 17x fewer gates were traded for 12% more qubits; Claude wrote the circuit designs as code, which an evaluator scored and iteratively revised, and it also proved new identities and verified them with formal proofs, making a classical mathematical shortcut work on quantum hardware for the first time.
Anthropic
Anthropic STEM Fellows Program: Claude Mythos 5 Designs More Efficient Quantum Circuits
Anthropic's STEM Fellows program has announced a result: Claude Mythos 5, when given natural language instructions, designed quantum circuits that outperform the best published solutions, with improvements of an order of magnitude or more in some cases. More efficient circuits can reduce the resources required for quantum algorithms, potentially enabling quantum computing applications in chemistry and materials science to land sooner.
Anthropic ResearchFirst-party
Anthropic has Claude autonomously design quantum circuits, with some results outperforming published approaches
Anthropic gave Claude plain-language specifications for eight quantum circuits along with an automated evaluator; in a closed loop with essentially no human intervention, Claude repeatedly submitted designs and improved them based on scores, finding solutions that use fewer qubits and gates than the best published circuits, with some improvements reaching an order of magnitude. The elliptic-curve modular inversion design came from a single 53-hour continuous run, in which Claude derived a reversible divsteps implementation that requires no storage of branch information and formally verified it with Lean; another effort reduced the gate count of the most expensive Reed-Solomon decoding step in DQI to about 1/12 of Google's previous construction. Anthropic also noted that Claude was initially conservative and tended to stick with known methods, which had to be mitigated by requiring parallel exploration of multiple approaches and occasionally prompting it to broaden its search.