2min chapter

The Inside View cover image

Tony Wang on Beating Superhuman Go AIs with Advesarial Policies

The Inside View

CHAPTER

The Future of Life in the Two

I don't think any of our systems are really or like in the future it could be like in three years we have something very capable that can do much more dangerous things. I'm not sure if you've seen in the video about the future of life in the two whether like a bunch of like different ais are controlling the some military aspects and I've seen this video. The simple version of jail breaks are like us. They're simpler in that it's easy to judge what the correct behavior is like because for instance like what with chat GPT. If a user asks it how to make a weapon, there's a clear answer as to what the model should do. It should always

00:00

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