Episode

"A Review of Anthropic’s Global Workspace Paper" by Neel Nanda

Podcast
LessWrong (Curated & Popular)
Published
Jul 9, 2026
Duration seconds
3055
Processing state
not_requested
Canonical source
https://www.buzzsprout.com/2037297/episodes/19468503-a-review-of-anthropic-s-global-workspace-paper-by-neel-nanda.mp3
Audio
https://www.buzzsprout.com/2037297/episodes/19468503-a-review-of-anthropic-s-global-workspace-paper-by-neel-nanda.mp3
JSON
/v1/public/podcasts/lesswrong-curated-popular-5643401/episodes/a-review-of-anthropic-s-global-workspace-paper-by-neel-nanda
Markdown
/podcast/lesswrong-curated-popular-5643401/a-review-of-anthropic-s-global-workspace-paper-by-neel-nanda.md

Actions

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

Summary

The below is a public review Anthropic asked me to write for their new global workspace paper. I recommend at least skimming their paper first. TLDR: I think this is a fantastic paper - it presents compelling evidence for some kind of "cognitive space" in models, that is used as a "working memory" for intermediate variables during a forward pass, shows that J-Lens is a useful technique for accessing this space. I believe these key claims.I believe J-Lens will be a useful (but limited) to...