Anthropic says it can read Claude's 'thoughts,' as detailed in new research paper — models observed to have a global workspace, revealing more of what makes LLMs tick

The story
Anthropic has discovered an internal "J-space" for its Claude AI that displays similarities to human internal processing. While the AI developer anthropomorphizes it as thought, it may yet prove useful as a method of improving LLM honesty, oversight, and guardrails.
How other outlets covered this
Compare allAlto found this story at 2 outlets. Same event, different framing — compare the headlines.
- VentureBeatQwen3.8-Max arrives with a bold claim: it outperforms GPT-5.6 Sol Max and Fable 5 on agentic computer use24 days ago
- Tom's Hardware Anthropic says it can read Claude's 'thoughts,' as detailed in new research paper — models observed to have a global workspace, revealing more of what makes LLMs tick about 2 months ago
How this story developed
Full timelineAlto has tracked this across 2 days of coverage from 2 outlets.
- Anthropic says it can read Claude's 'thoughts,' as detailed in new research paper — models observed to have a global workspace, revealing more of what makes LLMs tick You are here
Powered by Gab AI
The Story At A Glance
Reading this article now — analysis appears below
💡 AI analysis provides alternative perspectives on current events