Topic
Designing and operating real AI systems: agents, LLM applications, orchestration, memory, evaluation, AI governance, and local inference.
4 connected portfolio, venture, insight, and off-duty entries.
Can a transformer beat the MLP inside PPO and SAC? A three-way study placing the transformer on the actor, the critic, or both, with a CoordConv-ResNet encoder, the failure modes that shaped it, and held-out results across five agents.
A practical guide to tokenization and embeddings, covering BPE, WordPiece, Unigram, SentencePiece, word2vec, GloVe, fastText, contextual Transformers, and modern retrieval models.
A practical guide to agentic engineering for DevOps practitioners, covering harness, context, prompts, RAG, memory, tools, control loops, sandboxes, guardrails, observability, and evaluation.
A practical guide to the difference between agents, skills, and AGENTS.md—including how definitions, tools, permissions, and reusable workflows fit together in Codex.