post-training

paper ,  ai-ml-papers-of-the-week ,  agent-memory ,  trading-agents ,  post-training ,  wikiskill ,  compaction-cliff ,  physics-of-agents ,  scribes ,  abliteration-is-not-a-scalpel ,  generative-ai-floods ,  sharpness-aware-pretraining ,  life-bench ,  poisoning-agentic-alpha

qwen ,  mechanistic-interpretability ,  interpretability ,  post-training ,  sparse-autoencoder ,  sae ,  qwen-scope

openai ,  codex ,  reinforcement-learning ,  alignment ,  post-training ,  gpt-5-5 ,  behavior-audit ,  goblin

pdf ,  rlhf ,  course ,  dpo ,  llm-alignment ,  reinforcement-learning ,  epub ,  post-training ,  policy-gradient ,  open-source-book