One thing I would kind of caution on in this field is, you know, how do I make my machine learning system to have good enough quality that like it'll hit my 99% image detection threshold in real life or something like that? That's one standard. And there's this whole other standard, which is like, how do we build our machine learning systems to work well compared to like adversarial input? Right. Like, defensive design, like, defensive design. How do I defend against adversarial input?" He says he'd be "extremely skeptical" if they said a new fancy machine learning system will guard them from attack.

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