Today, we are launching Belief Updates, the Simplex research blog, with two posts.
Read the welcome post here:
And see our post about nonergodicy in the quote.
We are starting Belief Updates for a few reasons: 🧵👇
Show more
Training data for LLMs is made up of many sources. Given that, what structure should we expect in the activations?
New work from Simplex shows how the belief geometry over this type of data forms telescoping cones, and transformers represent them! 🧵👇
Show more
We need understanding more than we need tools.
