A RAG reranking design guide for AI Application Engineers. It distinguishes retrieval fusion, semantic reranking, business ranking, and evidence-set selection, then provides a production-ready default pipeline.
This article systematically explains context-compression methods for production AI agents, distinguishing message trimming, tool-result cleanup, artifact externalization, structured summaries, and native compaction. Using Hermes Agent, LangChain v1, and LangGraph v1, it presents a layered implementation and evaluation approach.
An intuitive introduction for programmers without a machine-learning background to gradient descent, loss functions, backpropagation, learning rates, and optimizers in LLM training, from next-token prediction through parameter updates.
Introduces OpenTelemetry’s core components and observability signals, and explains how to use them with AI agents, RAG, and production systems.
Drawing on Latent Space’s interview with Shunyu Yao, this article reviews ReAct, Reflexion, Tree of Thoughts, memory, benchmarks, ACI, and Agent UX, and summarizes the importance of tools, environments, evaluation, and interface design when putting AI agents into practice.
Starting from the trend of platforms absorbing basic RAG pipelines, this article examines the high-premium skills AI application engineers should prioritize in 2026: evaluation and observability, data governance and access control, and deep engineering capabilities for agentic workflows.
Using the bandwidth gap between hidden states and tokens, this article offers one explanation for LLM engineering phenomena such as Chain of Thought, prompt length, few-shot learning, personality drift, and hallucinations.
A systematic tour of the entire LLM training pipeline—from data pipelines, scaling laws, system constraints, synthetic data, distillation, post-training, and evaluation systems to agent training—and how these mechanisms affect model selection, evaluation, and harness design for AI application engineers.
Begin with a Comparison You ask ChatGPT, “What is a KV cache?” The model answers, and the conversation ends. You tell Codex CLI, “Add a user-authentication module to this project, including tests.” The agent begins working autonomously: read the project structure → understand the existing code → plan the implementation → write authentication logic → write tests → run tests → observe a failure → fix it → get the tests passing → open a pull request. The process may span dozens of steps without requiring your intervention. The underlying LLM may be the same, but the behavior is entirely different. The first is the traditional use of an LLM. The second is an agentic use. This article explains the nature of that transition. It is more than a stronger model. It is a fundamental shift in the way the model is used, and that shift reshapes the entire engineering system around it. ...
This article connects cross-entropy, perplexity, temperature, conditional entropy, hallucination detection, and prompt constraints into one line of reasoning, showing how entropy provides a unified language for understanding LLM training, inference, and product design. It also explains entropy’s practical value in RAG and engineering governance.