Training on knowledged.to

Training on knowledged.tohttps://knowledged.to/tags/training/Recent content in Training on knowledged.toHugoen-usWed, 24 Jun 2026 06:21:43 +0000RLVR vs. the Agent Loop: Training-Time vs. Inference-Timehttps://knowledged.to/ai/concepts/rlvr-vs-agent-loop/Wed, 24 Jun 2026 06:21:24 +0000https://knowledged.to/ai/concepts/rlvr-vs-agent-loop/Distinguishes RLVR as training-time weight updates from inference-time agent verification loops.The Modern LLM Training Pipelinehttps://knowledged.to/ai/concepts/modern-llm-training-pipeline/Wed, 24 Jun 2026 06:05:23 +0000https://knowledged.to/ai/concepts/modern-llm-training-pipeline/Explains the four-stage modern LLM training pipeline from pre-training through verifiable-reward RL.Where RL Fits: Training vs. Inference in the LLM Pipelinehttps://knowledged.to/ai/concepts/where-rl-fits-training-vs-inference-llm-pipeline/Wed, 24 Jun 2026 05:43:38 +0000https://knowledged.to/ai/concepts/where-rl-fits-training-vs-inference-llm-pipeline/Explains that RL in LLMs is a training/alignment stage, not inference, with pipeline context.