6 pages tagged

#post-training

constitutional-ai concept Anthropic alignment: written constitution + AI critique + RLAIF instead of per-example human labels. deliberative-alignment concept OpenAI alignment: model reasons about safety policy at inference time; reasoning-model-enabled. eval-grader-reward concept Training-time eval/grader/reward loop; ORM vs PRM; the grader is the critical failure point. grpo concept Group Relative Policy Optimization; drops PPO's value network; default for verifiable-reward RL. post-training concept SFT/RLHF/DPO/RFT routes; DeepSeek-R1 four-stage recipe; SFT teaches style as much as knowledge. 2026-04-27-llm-training-principles-paths-practices source Tw93's third essay: post-training, eval/reward, harness, distillation — the pipeline's back half.
esc