4min chapter

The Gradient: Perspectives on AI cover image

Raphaël Millière: The Vector Grounding Problem and Self-Consciousness

The Gradient: Perspectives on AI

CHAPTER

The Importance of Graularity in Language Models

Many of these chatbot-like systems certainly present as maybe having some kind of self-concept, at least if you ask it questions about itself. And this speaks to, I think, some human biases and the ways that we engage with things. The fact that language models use the first-past pronoun by default is probably responsible for a lot of the anthropomorphic attitudes people have towards these models.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode