Episode

"A global workspace in language models" by wesg

Podcast
LessWrong (Curated & Popular)
Published
Jul 7, 2026
Duration seconds
1983
Processing state
not_requested
Canonical source
https://www.buzzsprout.com/2037297/episodes/19455871-a-global-workspace-in-language-models-by-wesg.mp3
Audio
https://www.buzzsprout.com/2037297/episodes/19455871-a-global-workspace-in-language-models-by-wesg.mp3
JSON
/v1/public/podcasts/lesswrong-curated-popular-5643401/episodes/a-global-workspace-in-language-models-by-wesg
Markdown
/podcast/lesswrong-curated-popular-5643401/a-global-workspace-in-language-models-by-wesg.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/lesswrong-curated-popular-5643401/episodes/a-global-workspace-in-language-models-by-wesg/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/lesswrong-curated-popular-5643401/a-global-workspace-in-language-models-by-wesg.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

[This is the blog post for our new paper Verbalizable Representations Form a Global Workspace in Language Models Readers might also be interested in: the Public commentary, Github and Neuronpedia] As you read this sentence, circuits in your brain are adjusting your posture, controlling your breathing, and transforming lines and curves on the screen into recognizable words. Most of this processing is invisible to you. But some of what takes place in your brain you do have access ...