Stephen Casper

The AI risk repository: A meta-review, database, and taxonomy of risks from artificial intelligence

2026 · 28 Zit. · Patterns

Pitfalls of Evidence-Based AI Policy

2025 · 2 Zit. · SuperIntelligence - Robotics - Safety & Alignment

Diagnostics for Deep Neural Networks with Automated Copy/Paste Attacks

2022 · 1 Zit. · arXiv (Cornell University)

International AI Safety Report 2025: Second Key Update: Technical Safeguards and Risk Management

2025 · 1 Zit. · ArXiv.org

Cognitive Dissonance: Why Do Language Model Outputs Disagree with Internal Representations of Truthfulness?

2023 · 0 Zit. · arXiv (Cornell University)

The Singapore Consensus on Global AI Safety Research Priorities

2025 · 0 Zit. · ArXiv.org

Pitfalls of Evidence-Based AI Policy

2025 · 0 Zit. · ArXiv.org