NeuroAI researcher @ Amaranth Foundation, safety, open science. Previously engineer @ Google, Meta, Mila.

• Pinned

  

  Excited to release what we’ve been working on at Amaranth Foundation, our latest whitepaper, NeuroAI for AI safety! A detailed, ambitious roadmap for how neuroscience research can help build safer AI systems while accelerating both virtual neuroscience and neurotech. 1/N

  

• 

  There's a surprising amount of neurosymbolic work at the edge of capabilities in robotics. There's a case to be made that there are > 0 odds that (embodied) AGI won't look like undifferentiated end-to-end trained networks.

  

  

  00:00

• 

  This rules out many models of predictive coding

  

  1/ Update from the Lab: a multi-species, laminar-resolved test of Hierarchical Predictive Coding (HPC) in spiking activity. We (

  @jake_westerberg

  ,

  @SophyXiong

  , et al. ) recorded across the visual cortical hierarchy in NHPs (at Vanderbilt) and in mice at the Allen Institute via

• 

  We can't sprinkle AI on top of existing structures and expect *a country of geniuses in a datacenter* to then solve neuroscience. We need a clear-eyed view of how AI neuroscience is supposed to work. I wrote an optimistic but hype-free essay on what ought to be funded.

  

•