Laura Weidinger: Ethical Risks, Harms, and Alignment of Large Language Models
The Gradient: Perspectives on AI
00:00
What's the Main Insight From This Higher Level Synthesis?
There's a lot of work in measuring these harms with prior benchmarks. We don't have good measurement tools, so we really need to up our game and being able to measure what these harms look like. It's about understanding a bit more deeply what we're talking about," he says.
Transcript
Play full episode
