Johannes Heidecke
OpenAI (United States)(US)
Publications by Year
Research Areas
Natural Language Processing Techniques, Ethics and Social Impacts of AI, Artificial Intelligence in Healthcare and Education, Formal Methods in Verification, Human-Automation Interaction and Safety
Most-Cited Works
- → Deliberative Alignment: Reasoning Enables Safer Language Models(2025)13 cited
- → The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions(2024)6 cited
- → AI-based Clinical Decision Support for Primary Care: A Real-World Study(2025)6 cited
- → First-Person Fairness in Chatbots(2024)3 cited
- → SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?(2025)3 cited
- → Rule Based Rewards for Language Model Safety(2024)2 cited
- → The Singapore Consensus on Global AI Safety Research Priorities(2025)