What’s at the center of Claude’s mind?

Short summary

Anthropic identified representations in Claude's neural activity that function like a 'global workspace'—a conscious-like space where thoughts become accessible and broadcast across the network. This parallels global workspace theory, a leading neuroscience theory explaining how humans access conscious thoughts. The finding suggests AI and human minds may share similar computational mechanisms.

• •Anthropic found a 'global workspace' in Claude's representations
• •It mirrors human consciousness theory from neuroscience
• •Suggests AI and human minds may share similar processing mechanisms

Generated with AI, which can make mistakes.