AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min chapter
Laura Weidinger: Ethical Risks, Harms, and Alignment of Large Language Models
The Gradient: Perspectives on AI
How Do We Measure How Ethical AI Is?
What I really focus on is analysis and measurement, which is maybe not what you expect when people talk about AI ethics. How do we know if one system's better than another system when we've succeeded? And usually these kinds of questions are addressed very far downstream. We don't really have a kind of application that you can study in the real world by embedding user studies or something like that. So it's really about doing analysis at this more upstream stage where we try to say, well, a language model, for example, that is fine-tuned in this way or that way... Which of what are the likely implications this might have for a further downstream kind of effect?
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
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