Tag: anthropic

• How we contain Claude across products \ Anthropic

  May 27, 2026

  Anthropic is an AI safety and research company that’s working to build reliable, interpretable, and steerable AI systems. https://share.google/yf4rp2ehSGEetpg7P more ›

• Claude 4.5 Opus’ Soul Document

  December 3, 2025

  Richard Weiss managed to get Claude 4.5 Opus to spit out this 14,000 token document which Claude called the “Soul overview”. Richard says: While extracting Claude 4.5 Opus’ system message… more ›

• Emergent introspective awareness in large language models \ Anthropic

  October 29, 2025

  Research from Anthropic on the ability of large language models to introspect https://www.anthropic.com/research/introspection more ›

• Persona vectors: Monitoring and controlling character traits in language models

  August 3, 2025

  A paper from Anthropic describing persona vectors and their applications to monitoring and controlling model behavior https://www.anthropic.com/research/persona-vectors more ›

• Levers for Biological Progress

  November 10, 2024

  Dario Amodei, the CEO of Anthropic, recently published an essay called “Machines of Loving Grace.” It sketches out his vision for how AI could radically transform neuroscience, economics, diplomacy, and… more ›

• October 10, 2023

  Neural networks are trained on data, not programmed to follow rules. With each step of training, millions or billions of parameters are updated to make the model better at tasks,… more ›