There are definite cases where compute is somewhat of a bottleneck to ACDC and particular scaling it. Because our technique is like an iterative over all the nodes all the edges in fact which scale almost like with the square of the number of nodes involved currently this is not feasible at all for a gpt3 sized model. We're not able really to scale up an order of magnitude beyond gptu small at current but i'm excited for further interpretability research to hopefully scale to those sizes.

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