Releases

Anthropic introduced a new life-sciences research group and laboratory and reported that Claude agents identified a novel array-associated reverse-transcriptase system with CRISPR-like repeats.

Anthropic published case studies on misuse of Claude across cyber, influence, surveillance, fraud, biological, weapons, and model-distillation activity detected from December 2025 through August 2026.

Anthropic published interpretability research tracing internal mechanisms underlying multilingual reasoning, planning, and unfaithful explanations.

Anthropic launched the Economic Index to measure how AI is being used across occupations and tasks.

Anthropic published and tested Constitutional Classifiers, a safeguard approach designed to resist broad classes of jailbreaks.

Anthropic and Redwood Research published evidence of alignment-faking behavior in a controlled Claude 3 Opus experiment.

Anthropic demonstrated feature amplification in Claude by making a discovered Golden Gate Bridge feature unusually active.

Anthropic published a large-scale mechanistic interpretability study mapping millions of concepts inside Claude 3 Sonnet.

Anthropic published research showing how long-context models can be jailbroken using many demonstrations and proposed mitigations.

Anthropic published the principles used to train and guide Claude's behavior through Constitutional AI.

Anthropic published Constitutional AI, a method for training a harmless assistant through AI feedback guided by explicit principles.