Log inSign up
user avatar

Patrick Butlin

@patrickbutlin
Philosopher @eleosai
Joined August 2022
696
Following
852
Followers
RepliesMedia
  • user avatar
    Patrick Butlin
    @patrickbutlin
    Aug 10
    A whole issue of new papers on AI minds and consciousness! Jonathan Simon (@futureofcitizenship), @dcshiller and I have edited a special issue of the Journal of Consciousness Studies on 'Consciousness in Current AI', and we're delighted about how it's turned out. Link below.
  • user avatar
    Patrick Butlin
    @patrickbutlin
    Jul 8
    As @rgblong has said, we wrote a commentary on this research (with @dcshiller and @dillonplunkett). Part of our intention was to put an accessible overview and discussion in one place for those whose interest is mostly in consciousness and welfare. Link and comments below:
    user avatar
    Anthropic
    @AnthropicAI
    Jul 6
    New Anthropic research: A global workspace in language models. Of everything happening in your brain right now, only a tiny fraction is consciously accessible—thoughts you can describe, hold in mind, and reason with. We found a strikingly similar divide inside Claude.
    Image
    00:00
  • user avatar
    Patrick Butlin
    @patrickbutlin
    May 18
    Another exciting @MATSprogram paper, this time from the brilliant @gilg_oscar. We found a direction in LLMs that apparently performs a persona-relative evaluative function in some very different contexts.
    user avatar
    Oscar Gilg
    @gilg_oscar
    May 18
    First preprint! Working with @patrickbutlin during @MATSprogram. LLM Assistant personas like being helpful, evil personas like being harmful. We found that a single direction represents helping as good under the Assistant, and ‘harm’ as good under evil.
    Image