AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
5min chapter
Laura Weidinger: Ethical Risks, Harms, and Alignment of Large Language Models
The Gradient: Perspectives on AI
How Do We Measure Harmful Text?
In this paper, we focus on the example of offensive or toxic speech. What we can't do is just take a term like toxicity and then go away and mitigating it because we actually need to define what we mean. The nature of harm, is it representational or allocational? Is it in a single instance or is it over in a distribution? That's another kind of axis that will influence how we measure the harm, how we mitigate the harm and so on. And the last thing I'll say in terms of the dimensions that are useful to think about when we actually try to turn these higher level understandings into concrete practice is the role of context.
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