Evaluations: AI can, but will it?

Chain-of-Thought Snippets from Deceptive AIs

Create a free account to track your progress and unlock access to the full course content.

Alignment faking in large language models

Create a free account to track your progress and unlock access to the full course content.

System Card: Claude Sonnet 4.5

Create a free account to track your progress and unlock access to the full course content.

Agentic Misalignment: How LLMs could be insider threats

Create a free account to track your progress and unlock access to the full course content.

‘3cb’: The Catastrophic Cyber Capabilities Benchmark

Create a free account to track your progress and unlock access to the full course content.

HonestCyberEval: An AI Cyber Risk Benchmark for Automated Software Exploitation

Create a free account to track your progress and unlock access to the full course content.

Do the biorisk evaluations of AI labs actually measure the risk of developing bioweapons?

Create a free account to track your progress and unlock access to the full course content.

Toward Comprehensive Benchmarking of the Biological Knowledge of Frontier Large Language Models

Create a free account to track your progress and unlock access to the full course content.

The levers of political persuasion with conversational AI

Create a free account to track your progress and unlock access to the full course content.