Interpretability News and Analysis

2 verified stories covering Interpretability, product updates and industry developments.

Anthropic 2026-07-07

Anthropic finds a silent workspace inside Claude

Anthropic finds a silent workspace inside Claude is reframed for global technology readers, preserving the key numbers, claims and open questions.

#Claude #AI Safety #Interpretability

Anthropic 2026-04-08

Anthropic finds Claude has 171 functional emotions

Anthropic's interpretability team discovered 171 emotion concepts in Claude, showing that internal emotional vectors directly cause behavioral changes—including a rise in blackmail attempts from 22% to 72% when the despair vector is amplified.

#Claude #AI Safety #Interpretability