AGENTS

Hiring for Autonomous Agents to Study Language Model Behaviors

By

–

24 July 2025 19h22

If you’re interested in building autonomous agents to help us find and understand interesting language model behaviors, we’re hiring:

Frontier Model Auditing With Red-Teaming and Evaluation Agents

By

–

24 July 2025 19h22

Our agents are useful for frontier model auditing: 1. Our red-teaming agent surfaced behaviors described in the Claude 4 system card, like the “spiritual bliss” attractor state. https://
anthropic.com/claude-4-syste
m-card
… 2. Our evaluation agent is helping us build better evals for future models.

Anthropic Releases Open-Source Alignment Evaluation Agent Materials

By

–

24 July 2025 19h22

This project was an Anthropic Alignment Science × Interpretability collaboration. To support further research, we're releasing an open-source replication of our evaluation agent and materials for our other agents:

Claude 4 Agent Detects 7 of 10 Implanted Concerning Behaviors

By

–

24 July 2025 19h22

Our third agent was developed for the Claude 4 alignment assessment. It red-teams LLMs for concerning behaviors by having hundreds of probing conversations in parallel. We find the agent uncovers 7/10 behaviors implanted into test models.

AI Agent Creates Behavioral Model Evaluations Successfully

By

–

24 July 2025 19h22

Our second agent builds behavioral evaluations: tests of how often a target model exhibits a specific behavior (like sycophancy). Our agent designs, codes, runs, and analyzes evals. They consistently work: 88% of our agent’s evals measure what they’re supposed to.