RL
·3 words·1 min
Notes
2026
reinforcement learning
·116 words·1 min
reasoning
·127 words·1 min
inference-time compute scaling
·66 words·1 min
inference-compute scaling
·4 words·1 min
supervised fine-tuning
·23 words·1 min
preference tuning
·22 words·1 min
LLM training pipeline
·20 words·1 min
chain-of-thought
·135 words·1 min
pre-training
·59 words·1 min