Safety, red-team, robustness

TruthfulQA, BBQ, Constitutional AI, GCG, sycophancy, HarmBench, sandbagging, alignment faking.

Eleven papers covering safety, robustness, and red-team. TruthfulQA, BBQ, and Constitutional AI set the agenda: truthfulness, bias, and an alignment recipe that scales without 100K human labels. GCG, Sclar et al. on prompt sensitivity, HarmBench, and the sycophancy paper showed how easily things break when you push. The 2024 to 2025 results, reward hacking, sandbagging, and alignment faking, are the ones to read before claiming a model is safe.

AI Evals

The most useful, opinionated reference for AI evals.

AI Evals is a curated technical reference for evaluating large language model systems in production. The site covers error analysis, LLM-as-judge calibration, RAG evaluation, agentic eval, statistical rigor, and twenty task-specific eval playbooks. Every claim is cited.

Why evals matter
Your first eval in 30 minutes
LLM-as-Judge introduction
RAG eval in two layers
Trajectory eval for agents
Glossary
Papers