Log inSign up
user avatar

Logan Cross

@locross
Research Scientist, @GoogleDeepMind | Previously at @Stanford, and PhD in Computation and Neural Systems at @Caltech
London, England
locross93.github.io
Joined May 2009
4,252
Following
834
Followers
RepliesMedia
  • user avatar
    Logan Cross
    @locross
    Jun 4
    Excited to share our latest ICML 2026 paper: Solipsistic Superintelligence is Unlikely to be Cooperative We argue that AI systems trained as isolated optimizers struggle during deployment in this fundamentally multi-agent reality. Why? The world pushes back. Humans adapt.
    user avatar
    Rakshit Trivedi
    @rstriv
    Jun 4
    As increasingly capable AI systems are deployed, humans, institutions, and other AI systems adapt in response — i.e. the world pushes back. So is capability still the central safety challenge for AI? We think not. We believe the harder challenge is coexistence. The current AI
    Image
  • user avatar
    Logan Cross
    @locross
    Mar 16
    Ever wonder why we drop $1,000s on a Chanel bag or queue for ages for a Labubu doll? Status signaling drives a lot of human behavior, but how certain things become potent status symbols has a remained a big puzzle in social science In our new paper we: 1. Synthesize the
    Image
  • user avatar
    Logan Cross
    @locross
    Feb 24
    Check out our latest paper! LLM-based social simulation is promising — but generic persona prompting collapses toward the “average human,” failing to capture the rich distribution of real behavior. In Persona Generators, we introduce: • A two-stage pipeline: 1.Generate thin
    user avatar
    Davide Paglieri
    @PaglieriDavide
    Feb 16
    🧬 New paper from my internship at @GoogleDeepMind We introduce Persona Generators: functions that generate diverse synthetic populations for arbitrary contexts. We use AlphaEvolve to optimize the generator code, hill-climbing on diversity metrics — not just likelihood —
    Image
  • user avatar
    Logan Cross
    @locross
    Aug 12, 2025
    How do we predict what others will do next? 🤔 We look for patterns. But what are the limits of this ability? In our new paper at #CCN2025, we explore the computational constraints of human pattern recognition using the classic game of Rock, Paper, Scissors 🗿📄✂️
    Image