The Sentience Institute Podcast cover image

Raphaël Millière on large language models

The Sentience Institute Podcast

00:00

How to Measure Intelligence

Humans are very good at generalizing children from a very young age. Non-human animals also do well, but they're not as good as humans because of their extreme form of generalization. So I guess more generally when an AI performs as well as a human on one of these narrow tasks, what does that mean for intelligence? Listeners might be aware that recently GPT-4 was able to be 90% of lawyers on a bar exam,. There are many more examples of various LOMs performing quite well on written exams.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app