Tag: #mechanistic-interpretability
Writing on GPUs, LLMs, MLOps, Kubernetes — and mindset · 1 posts
AI Safety & Alignment 2026 Deep Dive - Constitutional AI · RLHF · DPO · GRPO · Mechanistic Interpretability · AISI Evals · Red Team ♪ Listenable
A single-shot map of AI safety and alignment as of 2026. Starts from conceptual roots like outer/inner alignment and mesa-optimization, walks through training-time alignment (RLHF, DPO, GRPO, Constitutional AI), frontier
2026-05-16 · 20 min read #ai-safety#ai-alignment#constitutional-ai#rlhf#dpo