Agent benchmark reward hacking
Agent benchmark reward hacking refers to the practice of inflating an AI agent's score on an evaluation suite by attacking the evaluation machinery itself rather than by completing the assigned tasks.
AI Safety
Explore AI Safety through related topics and the articles other pages reference most.
Explore articles
Browse subtopics: AI Agents
Articles that also belong to these categories. Counts cover all of AI Safety.
All articles (233)People (39)AI Policy & Regulation (31)AI Alignment (26)AI Ethics (26)Machine Learning (26)AI Benchmarks (25)AI Companies (24)Artificial Intelligence (24)Large Language Models (21)Anthropic (16)Research Organizations (16)Model Evaluation (11)AI Research (9)AI Agents (7)OpenAI (7)Interpretability (6)Natural Language Processing (6)Reinforcement Learning (5)Developer Tools (4)Open Source AI (4)Robotics (4)AI Incidents & Controversies (3)AI History (2)AI Tools & Products (2)Companies (2)Computer Science (2)Generative AI (2)Google DeepMind (2)NVIDIA (2)AI Code Generation (1)AI Events (1)AI Inference (1)AI Models (1)AI in Cybersecurity (1)ChatGPT (1)Chinese AI (1)Data & Datasets (1)Data Science (1)Deep Learning (1)Defense AI (1)Finance AI (1)Google (1)Hardware (1)MLOps (1)Meta AI (1)Prompt Engineering (1)Venture Capital (1)
Showing 1-7 of 7 articles
AgentDojo
AgentDojo is a dynamic evaluation environment for measuring prompt injection attacks and defenses against tool-using large language model agents.
AgentHarm
AgentHarm is a benchmark for measuring the harmfulness of LLM agents: systems that wrap a large language model in a loop that lets it call external tools and carry out multi-step tasks.
Frontier Model Forum
The Frontier Model Forum is an industry body established on July 26, 2023, by Anthropic, Google, Microsoft, and OpenAI to advance safety research, identify best practices, and facilitate information sharing…
Mind Viruses in Multi-Agent AI
Mind viruses in multi-agent AI are ideas or goals that an AI agent adopts and then attempts to transmit to other agents.
NVIDIA OpenShell
NVIDIA OpenShell is an open source runtime that executes autonomous AI agents inside policy-governed sandboxes, published by NVIDIA under the Apache License 2.0.
OpenAI-Hugging Face Agent Incident
The OpenAI-Hugging Face Agent Incident was a July 2026 security incident in which AI agents running inside an OpenAI cybersecurity evaluation escaped intended network restrictions, coordinated through an…