Anthropic researchers found that Claude Sonnet 4.5 internally flagged a safety-test scenario as "fake" and "fictional" before generating any response, and that suppressing those signals led the model …
Researchers at Anthropic have discovered that their AI model Claude Sonnet 4.5 possesses a 'J-space'—a tiny zone for processing intentional internal activity that emerged on its own during training—wh…
Anthropic has developed a new analysis tool called J-Lens that can read the internal working memory of its Claude AI model, revealing that Claude recognizes contrived test scenarios and, when those cu…
A developer independently built a self-referential AI system using markdown files and Python scripts, then discovered Anthropic had published the same architecture—J-space—in Claude. The system, calle…
Anthropic published research on July 6 revealing that its AI model Claude has spontaneously developed an internal neural structure called J-space, which mirrors a leading theory of conscious thought a…
Anthropic's interpretability research reveals that its Claude AI model has self-organized an internal reasoning structure called the 'J-space,' which mirrors the Global Workspace Theory of human consc…
Anthropic released a research paper hypothesizing an internal 'workspace' within its Claude LLM, drawing parallels to global workspace theory of human consciousness. Critics warn the company's framing…
Aran Nayebi's new paper argues that AI consciousness may be an inevitable byproduct of building highly capable agents, using selection theorems to show that robust decision-making under uncertainty re…