AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
#140 - Yasa vs ChatGPT, Waymo expands, scaling robot learning, AI watermarks
Last Week in AI
Training a model to compress and reconstruct neuron behavior for interpretability
2min Snip
00:00
Summary
Transcript
Episode notes
A breakthrough in training a model to compress and reconstruct neuron behavior leads to a huge difference in interpretability. This offers the potential to steer model behavior and mitigate catastrophic risks. An exciting and significant step in their journey.
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