The adversarial problem, right? Like, it's totally unfair to the AI in some important sense that we're judging them this way. So what I bottom line that to basically robustness if I had to add another category is sort of adversarial out of distribution. And I would also be resilient or some form of that. But you can't run that attack on us. Right, like, you don't get to do that. You know, it's only a matter of time before you figure out every little quirk and putting off into so much easier than playing defense.

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