Alzheimer's is a terrible thing to go through. I was thinking about how we can help Alzheimer's from the care side rather than the disease and cure side. I wonder if a sort of Notebook LM for memories that would be built early on help someone maintain understanding and connection...
Increasing Skill Level Recruits Deeper Attention Layers in a Frozen Chess Transformer Paper: https://arxiv.org/abs/2609.23917 TL;DR: Maia-3 is a transformer-based chess model that takes Elo (the standard metric for chess skill) as an input to the pre-trained network, so you can vary the skill the network is conditioned on with no...
Paper: Increasing Skill Level Recruits Deeper Attention Layers in a Frozen Chess Transformer TL;DR: Maia-3 is a transformer-based chess model that takes Elo (the standard metric for competitive chess skill) as an input to the pre-trained network, so you can vary the skill the network is conditioned on with no...
Hi, I am trying to more precisely understand some ideas in mathematical logic and find myself drowning a bit in self referential formal logic and theorems by Lob, Tarski, Kripke, Godel... Looking at Curry's Paradox: 1) Let F be: "if this sentence is true then Santa exists" 2) Assume F...
Summary This is the third and final post in a series detailing our attempts to mechanistically interpret one head of the chess transformer Maia-3. We find that previous causal evidence gave us a spurious picture of the head, and that rather than just detecting knight forks, head 5 of layer...
Summary of this post This is the second in a series of posts detailing my manifold findings while investigating how a chess transformer engine that mimics human play represents knight forks. Last post described strong correlational evidence that the knight-fork policy logit snaps into place after block 5’s attention layer....
I was poking around at a chessformer which mimics human play and made companion app to visualize a lot of the internals of the engine. Check out how attention heads look, how the residual stream evolves, and play around with it if interested! Quickest path to run it: pip install...