Part 2 of the TED Radio Hour episode Decoding nature’s hidden patterns.
Computational linguist Jeff Reed figured out how to eavesdrop on wolves in the wild. But he needed help from AI to separate the signal from the noise, and start to decode what each howl means.
About Jeffrey Reed
Jeffrey Reed has a PhD in ancient languages and spent three decades in Silicon Valley — building machines that could replicate human language. A few years ago he moved back to his hometown on the outskirts of Yellowstone National Park and began using AI and bioacoustics to isolate, record, and interpret the sounds that wolves make in the wild. He co-founded The Cry Wolf Project, the world’s largest bioacoustics study of wild wolves. He also co-founded Grizzly Systems, a company that makes the technology required for monitoring wildlife. His book on wolf communication is forthcoming from Little, Brown and Company.
This segment of the TED Radio Hour was produced by Phoebe Lett and edited by Sanaz Meshkinpour. You can follow us on Facebook @TEDRadioHour and email us at TEDRadioHour@npr.org.
Web Resources
Related TED Talk: Can we learn to talk to sperm whales?
Related TED Topic: Biodiversity
Related TED Talk: How I imitate nature’s voices
Related NPR Links
TED Radio Hour: What are animals saying to each other? AI can help us eavesdrop
Short Wave: What is the legacy of Yellowstone wolves 30 years after their reintroduction?
TED Radio Hour: Can the insect brain help us develop smarter, faster AI?
Copyright 2025 NPR
