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

episode

Nature Podcast not yet transcribed

▲ 0

Transcript

This episode hasn't been transcribed yet Upvotes decide what gets transcribed next — 0 so far. Sign in to upvote

More from Nature Podcast

Audio long read: Could mending damaged DNA prolong life? 18 min · 02 Sep 2026

Briefing Chat: How Dolly Parton left her mark on science 14 min · 28 Aug 2026

Highest-ever ocean temperatures recorded as El Niño intensifies 19 min · 26 Aug 2026

Briefing Chat: New narcolepsy drug could unlock host of novel brain therapies 12 min · 21 Aug 2026

A black hole's spin could finally be measured by a high-speed star 29 min · 19 Aug 2026

Briefing Chat: Anthropic rolls out new AI watermark — will it make a difference? 16 min · 14 Aug 2026

All episodes from Nature Podcast →

Report any issue

Source

Recorded24 May 2024

Publisherfeeds.acast.com ↗

Handlerec:12318667

Show notes

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.

Ask this episode

“What did the council decide on item 42?” — answered with the speaker and the moment.

Sign in