Anthropic explains how Claude's thoughts split into conscious and automatic levels
Original titleThe different levels of how Claude thinks
AISummary
Anthropic presents research finding a set of representations in Claude's neural activity that resembles the global workspace theory from neuroscience. The video explains how these representations separate thoughts that are consciously accessible from automatic processing, with a full write-up linked from the source.
AIWhy it matters
The video explains how Anthropic tested a global workspace analogy inside Claude's neural activity, which bears on how model internals are studied.
Source: Anthropic · YouTube · youtube.comPublished · added here