The frontier models are performing so much better is they probably have a lot cleaner data set than some of the earlier open source stuff that is accessible for this kind of work but because they have such a mess. There's all these kind of sub circuits running in superposition on top of each other and so actually there are if when you zero in on this task it is actually reasonable to expect that there is some sub circuit that in isolation could do a better job than the model itself is doing. The goal with defining a task specific metric is to zero in on that perhaps even better than baseline model performance by stripping away this other stuff that in fact might be hurting overall performance on this test yeah exactly I

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