https://academy.animestan.co/2026-10-16 https://academy.animestan.co/episode/ep01-what-is-an-llm https://academy.animestan.co/episode/ep02-transformer-attention https://academy.animestan.co/episode/ep03-kv-cache https://academy.animestan.co/episode/ep04-inference-servers https://academy.animestan.co/episode/ep05-paged-attention https://academy.animestan.co/episode/ep06-optimization-toolbox https://academy.animestan.co/episode/ep07-mixture-of-experts https://academy.animestan.co/episode/ep08-deepseek-architecture https://academy.animestan.co/episode/ep09-glm-architecture https://academy.animestan.co/episode/ep10-bert-encoder-models https://academy.animestan.co/episode/ep11-whisper-speech https://academy.animestan.co/episode/ep12-will-it-fit https://academy.animestan.co/episode/ep13-serving-vllm https://academy.animestan.co/episode/ep14-serving-sglang https://academy.animestan.co/episode/ep15-deploying-diffusers https://academy.animestan.co/episode/ep16-slurm-hpc https://academy.animestan.co/episode/ep17-finetuning-llms https://academy.animestan.co/episode/ep18-evaluation-metrics https://academy.animestan.co/episode/ep19-llm-as-a-judge https://academy.animestan.co/episode/ep20-rag-zero-to-hero https://academy.animestan.co/episode/ep21-advanced-rag-agents https://academy.animestan.co/episode/ep22-aiops-llmops https://academy.animestan.co/episode/ep23-prefill-vs-decode https://academy.animestan.co/episode/ep24-chunked-prefill-prefix-caching https://academy.animestan.co/episode/ep25-attention-variants-mla https://academy.animestan.co/episode/ep26-engram-lookup-tables https://academy.animestan.co/episode/ep27-chunking-strategies https://academy.animestan.co/episode/ep28-embeddings-vector-search https://academy.animestan.co/episode/ep29-reranking-context-engineering https://academy.animestan.co/episode/ep30-debugging-rag https://academy.animestan.co/episode/ep31-tool-calling https://academy.animestan.co/episode/ep32-agentic-loops-integration https://academy.animestan.co/episode/ep33-langchain-langgraph https://academy.animestan.co/episode/ep34-model-context-protocol https://academy.animestan.co/episode/ep35-multimodal-vlm https://academy.animestan.co/episode/ep36-reasoning-models https://academy.animestan.co/episode/ep37-eval-harnesses https://academy.animestan.co/episode/ep38-guardrails-safety https://academy.animestan.co/episode/ep39-production-mlops-llmops https://academy.animestan.co/episode/ep40-optimization-decision https://academy.animestan.co/episode/ep41-sampling-decoding https://academy.animestan.co/episode/ep42-llm-gateways-routing https://academy.animestan.co/episode/ep43-what-is-a-coding-agent https://academy.animestan.co/episode/ep44-inside-the-agent-harness https://academy.animestan.co/episode/ep45-coding-tools-landscape https://academy.animestan.co/episode/ep46-customizing-your-agent https://academy.animestan.co/episode/ep47-learning-building-with-agents https://academy.animestan.co/episode/ep48-where-to-get-models https://academy.animestan.co/episode/ep49-production-finetuning https://academy.animestan.co/episode/ep50-model-benchmarking https://academy.animestan.co/episode/ep51-production-evaluation https://academy.animestan.co/episode/ep52-which-machine-which-model https://academy.animestan.co/episode/ep53-cheaper-alternatives https://academy.animestan.co/episode/ep54-long-context https://academy.animestan.co/episode/ep55-on-device-edge https://academy.animestan.co/episode/ep56-llm-security https://academy.animestan.co/episode/ep57-alignment-continuous-learning https://academy.animestan.co/episode/ep58-beyond-transformers https://academy.animestan.co/episode/ep59-jev-system-one