AI Alignment

A diary entry covering AI personalities, utility engineering for emergent value systems, and methods for evaluating the goal-directedness of Large Language Models (LLMs).

A diary entry on AI risks, including misalignment, misuse, and s-risks, and an exploration of emergent misalignment due to prompt sensitivity in LLMs.

A diary entry on longtermism and its moral implications for the future, and a paper on teaching models to verbalize reward hacking in Chain-of-Thought reasoning.

A diary entry on common use cases for AI models and the risks of models obfuscating their reasoning to evade safety monitors.

A diary entry on advanced prompt engineering techniques and the faithfulness of LLM self-explanations for commonsense tasks.

A diary entry on how Chain-of-Thought (CoT) reasoning affects LLM’s ability to evade monitors, and the challenge of unfaithful reasoning in model explanations.

A diary entry on Chapter 5 of the AI Safety Atlas, focusing on evaluation methods for assessing the safety and alignment of advanced AI systems, including benchmarks and robustness testing.

A diary entry on ‘Alignment Faking’ in Large Language Models (LLMs), exploring how models can superficially appear aligned while pursuing misaligned goals, and methods for detection and mitigation.

A diary entry on tracing the reasoning processes of Large Language Models (LLMs) to enhance interpretability, and a discussion on the inherent difficulties and challenges in achieving AI alignment.

A diary entry on the audio version of Chapter 3 of the AI Safety Atlas, focusing on strategies for mitigating AI risks, including technical approaches like alignment and interpretability, and governance strategies.