DeepMind’s Deep Loop Shaping cuts LIGO control noise 30–100×
Result confirmed
The takeaway
In Science (Sept 2025), DeepMind, LIGO/Caltech and GSSI reported an RL control method trained with frequency-domain rewards.
Status
- Claim
Result confirmed
- Our reporting
- High confidence
- Verification
- Peer-reviewed
- Importance
- 3 of 5
- Last verified
- 29 September 2026
Your AI and this story
- GPT-6.2 AstraIn its training data
- Claude Opus 5.5In its training data
- Gemini 4 HydrogenIn its training data
- Grok 4.7In its training data
It happened before the cutoffs of all four assistants, so it can be in their training data.
Key facts
- >30× noise reduction in the 10–30 Hz observation band (up to 100× in sub-bands)
- Demonstrated on LIGO Livingston hardware
- Could let LIGO detect more and heavier black-hole mergers and intermediate-mass black holes
What happened
An RL controller learned to stabilise LIGO’s mirrors while injecting far less noise into the frequencies where gravitational waves are measured.
Why it matters
It extends the reach of one of physics’ most sensitive instruments without new hardware.
Sources
2 sources from 2 sites. Numbers match the chips in the text.
2 sources: 1 primary, 1 press
Primary
- Improving cosmological reach of a gravitational wave observatory using Deep Loop Shaping (Science)science.org, paper
Press
- Caltech: Artificial intelligence helps boost LIGOcaltech.edu, press
Changes
- Filed