AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
How worried—or excited—should we be about AI?
Channels with Peter Kafka
The Limits of Guardrails for Generative Errors
I think it's very important to be thinking about the ways these systems could either be incorrect or biased or toxic. So in our case, we do a lot of generative adversarial testing of these systems. In fact, when you use BOD, for example, the output that you get when you type in a prompt is not necessarily the first thing that BOD came up with,. We're running 15, 16 different of the same prompt to look at those outputs and pre-assess them for safety.
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