BREAKING
Anthropic Finds 'Global Workspace' in Claude
0%
of activations (under)
0+
concepts at a time
How Claude Uses This Space
1Silent thought forms
2Steps surface in space
3Edit steps
4Output changes
Delete the Workspace: What Breaks
Survives
Fluent text generation
Degradessharp
Multi-step reasoning
Summarization
Planning
A Safety Lead, With Caveats
Research Stage, Paper Unconfirmed
AI NEWS BLITZ
Anthropic says it can observe a global workspace inside its Claude models.