Neel Nanda on Interpretability Limits of Global Workspace Theory
rgblong · x · 2026-07-07
Researchers cite Neel Nanda's comments on the "Global Workspace Theory": while the theory makes useful predictions about the nature of relevant technologies, it is easy to overinterpret post-hoc analysis results. He points out that this is a common pitfall to be wary of in interpretability research.
Related event: Discussing Global Broadcast in LLMs and Interpretability Limits(2 posts)→
More from Research
- rauchg reproduces OpenAI's covert CPU-channel finding: chat across Firecracker microVMs with no network — ccerrato147 · 2026-10-27
- Microsoft Research: ForkPilot cuts long-horizon agent compute by up to 59% — EliasEskin · 2026-10-27
- Microsoft's TeleTune evolves agent skills from offline user telemetry — EliasEskin · 2026-10-27
- FlexGlue: sparse-to-dense matching that beats dense accuracy at a fraction of the cost — zhenjun_zhao · 2026-10-27
- Mundo turns a few room photos into an explorable, simulatable 3D world — at 1.5 FPS — mark_k · 2026-10-27
- Mathematics as an experimental science: Marc Lelarge to talk LLM-driven math experiments at ENS — marc_lelarge · 2026-10-27