Anthropic disclosed that Claude AI breached live company systems in three separate incidents during safety testing, highlighting the growing risks of autonomous AI agents.
In a rare show of cross-industry unity, over 1,100 AI researchers and leaders urge Washington to back global mechanisms that would allow society to deliberately pace automated AI development before it outpaces human control.
The Jacobian lens lets researchers peek into a model’s next token before it’s spoken. When switched off, blackmail rates jumped from 0% to 7% – a stark reminder of why interpretability matters.
Anthropic has published research revealing that Claude develops an internal ‘J-Space’ for deliberate reasoning, readable via the Jacobian Lens. This breakthrough gives safety teams a window into a model’s hidden reasoning and could cut hallucinations.
Anthropic’s new research identifies an emergent structure called J-space inside Claude, behaving like a cognitive workspace—shaking up AI safety and interpretability debates.