Audio long read: How does ChatGPT ‘think’? Psychology and neuroscience crack open AI large language models

Nature Podcast
24/05/2024 17 min
Audio long read: How does ChatGPT ‘think’? Psychology and neuroscience crack open AI large language models

Listen "Audio long read: How does ChatGPT ‘think’? Psychology and neuroscience crack open AI large language models"

Descargar episodio Ver en sitio original

Episode Synopsis

AIs are often described as 'black boxes' with researchers unable to to figure out how they 'think'. To better understand these often inscrutable systems, some scientists are borrowing from psychology and neuroscience to design tools to reverse-engineer them, which they hope will lead to the design of safer, more efficient AIs.This is an audio version of our Feature: How does ChatGPT ‘think’? Psychology and neuroscience crack open AI large language models Hosted on Acast. See acast.com/privacy for more information.

More episodes of the podcast Nature Podcast

Audio long read: How to get the best night’s sleep — what the science says 24/10/2025
Honey, I ate the kids: how hunger and hormones make mice aggressive 22/10/2025
New bird flu vaccine could tackle multiple variants with one shot 15/10/2025
How stereotypes shape AI – and what that means for the future of hiring 08/10/2025
Ancient viral DNA helps human embryos develop 01/10/2025
Audio long read: Autism is on the rise — what’s really behind the increase? 26/09/2025
How a dangerous tick-borne virus sneaks into the brain 24/09/2025
Apocalypse then: how cataclysms shaped human societies 19/09/2025
This AI tool predicts your risk of 1,000 diseases — by looking at your medical records 17/09/2025
Detecting gravitational waves 12/09/2025
© 2003-2025 ZARZA | AHEAD OF OUR TIME
privacy policy
In God we trust In God we trust
PreSales Questions? Click Here
or call our toll-free line at +1-888-5002068 Miami, Florida, USA