Can AI write a quantum circuit's settings? (QAOA pilot)
On 64 held-out graphs (CPU simulation), a learned model wrote QAOA angles with a mean approximation ratio of 0.766 versus 0.812 for one fixed angle set. The pilot is valid; the learned generator missed.
Key numbers
mean approximation ratio, p=1 (learned vs fixed)
0.766 vs 0.812Source file:
Source hash:
qaoa-weightgen/runs/2026-10-13-pilot/summary.jsonSource hash:
706df148f5f02d81Caveats
- Pilot on one graph family; per-graph optimisation beats fixed angles by only about 0.007
Watch the roundup
What we tested, and what we learned (90 s)
Video hash: 3de55bc330bba5f8
Request the full write-up
Full write-ups are not public yet. You can request one; requests are reviewed by hand.
Requests are stored privately for up to twelve months, reviewed by hand, never shared, and deleted on request. Contact QMAI@quantummindaillc.com.