Anthropic’s global-workspace paper hints at a fixed semantic coordinate system in LLMs
tszzl · x · 2026-07-26
- The author argues that Anthropic’s recent paper on global workspaces in LLMs sheds light on the Chinese Room puzzle.
- The most striking result is that averaging Jacobians across contexts can still produce a meaningful readout for which word a token would generate at a given layer.
- That suggests intermediate LLM representations may live in a shared, fixed coordinate system for meaning, rather than changing arbitrarily with context.
- In this view, different layers communicate in a common semantic language before producing the final output.
More from AGI Musings
- AI debate framed as a replay of Industrial Revolution-era reactions — joshua_saxe · 2026-07-26
- The model matters less than what you do with it, says AI watcher — StewartalsopIII · 2026-07-26
- Forced AI adoption is creating a market for opt-out workshops — HaktanSuren · 2026-07-26
- Artificial Analysis chart puts frontier AI on a 12.1-month doubling curve — christopher534 · 2026-07-26
- Microsoft, Palantir and Nvidia CEOs are all leaning into the case for companies — teortaxesTex · 2026-07-26
- Bittensor’s open subnet model pits 256 miners against each other for payouts — markjeffrey · 2026-07-26