4 min listen
Audio long read: How does ChatGPT ‘think’? Psychology and neuroscience crack open AI large language models
FromNature Podcast
Audio long read: How does ChatGPT ‘think’? Psychology and neuroscience crack open AI large language models
FromNature Podcast
ratings:
Length:
18 minutes
Released:
May 24, 2024
Format:
Podcast episode
Description
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.
Released:
May 24, 2024
Format:
Podcast episode
Titles in the series (100)
Nature Podcast Extra: Futures: Futures is Nature's weekly science fiction slot. Now its sister title Nature Physics has followed suit, publishing a sci-fi story each month. Kerri Smith reads you this month’s tale, The stuff we don’t do, by Marissa Lingen. by Nature Podcast