Open Threads are informal discussion areas, where users are welcome to post comments that didn't quite feel big enough to warrant a top-level post, nor fit in other posts... (read more)

AI Evaluations, or "Evals", focus on assessing the capabilities, safety, and alignment of advanced AI systems. These evaluations can be divided into two main categories: behavioral and understanding-based... (read more)

Löb's Theorem is theorem proved by Martin Hugo Löb which states: .. (read more)

Emotivism is a meta-ethical model. It's central claim is that moral statements do not express propositions but emotional attitudes.

Reinforcement Learning from Human Feedback (RLHF) is a machine learning technique where the model's training signal uses human evaluations of the model's outputs, rather than labeled data or a ground truth reward signal.

An alignment tax (sometimes called a safety tax) is the extra cost of ensuring that an AI system is aligned, relative to the cost of building an unaligned alternative. The term ‘tax’ can be misleading: in the safety literature, ‘alignment/safety tax’ or ‘alignment cost’ is meant to refer to increased developer time, extra compute, or decreased performance, and not only to the financial cost/tax required to build an aligned system... (read more)