Anthropic Just Found a Dangerous New AI Behavior

Anthropic found a hidden 'workspace' inside Claude

Anthropic has built something close to a mind-reading tool for its own AI. What it found sits somewhere between a breakthrough and an unsettling party trick. Anthropic researchers now have the clearest view yet of what a large language model does while it thinks. In a paper published on the company’s Transformer Circuits site, they […] This story continues at The Next Web

Anthropic Just Found a Dangerous New AI Behavior

Anthropic just raised new AI safety questions with its latest workspace research. On July 6, 2026, the company published new findings. Claude, it says, runs a hidden Anthropic workspace called “J-space.” There, the model silently holds concepts before a word reaches the screen. Sometimes it registers something its final answer never mentions. Inside Claude’s Secret Workspace Anthropic built a new interpretability tool called the Jacobian lens, o…

Thinking Very Carefully About Whether Anthropic Found The Seat Of AI Consciousness

Anthropic found an intriguing inner working element of modern LLMs. Does this give light to the advent of AI consciousness. An AI Insider analysis and scoop.

Anthropic found a hidden space where Claude puzzles over concepts

The AI firm Anthropic has developed a technique that has given it the clearest glimpse yet at what’s really going on inside large language models as they answer questions or carry out tasks. What they found ranges from the mundane to the unnerving. Researchers at the company built a tool called the Jacobian lens (or…

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

Anthropic has discovered evidence that its Claude AI models use an internal reasoning space to respond to prompts that mirrors some of the internal processing of human consciousness. Using its Jacobian Lens, or J-Lens technique, to peer into the way Claude processes information and reasons its way to a response to user prompts, Anthropic can interpret this "J-Space," and showcase what might be going on under Claude's previously-opaque surface. T…

Claude Just Crossed The Consciousness Line And Anthropic Admitted It

Claude may have just crossed the consciousness line. Anthropic found a hidden workspace inside Claude where thoughts appear before answers, and it could change how we understand AI reasoning, safety, and hidden intent. Credit to : AI Revolution