Anthropic paper: verbalizable representations form a global workspace in LLMs

gleech · x · 2026-09-24

Anthropic's new Transformer Circuits paper argues LLMs maintain a privileged set of verbalizable representations — available for report, modulation, and flexible reasoning — atop a larger volume of automatic processing, mirroring the conscious/unconscious split in human cognition.

Original post →

More from Safety

Safety channel →