AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
4min chapter
Irina Rish–AGI, Scaling and Alignment
The Inside View
The Loss-Lanscape
There's something about validation laws and training laws, where the validation laws goes down much later than training laws. What happens, what are properties of the task or what is property of the solutions? In the trajectory, it's a very interesting area of research, actually. We're looking at some properties that precede that somewhat relate to oscillations in the loss,. And some other things, while we still have to work on that paper. I'm also really looking forward to reading recent paper from Max Group.
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