Skip to content

Articles

Technical articles on production LLM systems: data integration, reliable agents, evaluation, and recovery.

Is Saying an LLM Doesn't Think Like Saying a Calculator Can't Do Numbers?

Where the calculator analogy for LLMs holds and where it breaks: what interpretability, chain-of-thought and philosophy of mind say about thinking.

Jul 2, 202616 min read
#LLM#AI Reasoning#Interpretability#Philosophy of Mind

Running a Small Language Model on an Xbox Series S

An engineering report on porting a small language model to an Xbox Series S: what runs at 71 tok/s on the Zen 2 CPU, and the constraints I have not solved yet.

Jun 26, 20269 min read
#Edge Inference#On-Device AI#ONNX Runtime#Xbox#SLM#UWP

What Bank-Grade Key Management Teaches You About Agent Eval Harnesses

Five disciplines from banking security — durable state, deterministic recovery, dual control, and audit trails — applied to LLM agent evaluation.

Apr 18, 20265 min read
#Agent Evals#Verifiable Systems#LLM Production#Banking#MCP

Where CrewAI Breaks in Production — and What to Use Instead

The role abstraction in CrewAI works for demos and struggles under production load. Four specific failure modes and the LangGraph patterns that replaced them.

Jan 15, 202510 min read
#CrewAI#Multi-Agent#LangGraph#Production
Read on MediumRSS feed