The Model Is Not the Moat: Reading Nadella's Note
Satya Nadella's note on human and token capital isn't about agents. It's about owning the learning loop — the asset interchangeable models can't commoditize.
Read article → Architecture
6 Posts
Exploring architecture and related topics
Filter by Topic
All AI AI Agents AI Architecture AI Engineering AI Evaluation AI Literacy AI/ML Agent Harness Agentic AI Agentic Workflows Agents Anthropic Architecture Automation Benchmarks Best Practices Blockchain Career Claude Claude Code Codex Data Quality Developer Productivity Development Engineering Eval Generation Feedback Loops Gemini Governance LLM LLM API Leadership MLOps Machine Learning OpenAI Production Production AI Prompt Engineering Python RAG SOTA Security Self-Improving AI Structured Prompting Supply Chain Systems Thinking Testing Versioning npm
What Happens When You Call an LLM API
· 12 min read
Your prompt travels through 7 infrastructure layers before a single token comes back. A plain-language walkthrough of API gateways, tokenization, prefill, decode, post-processing, billing, and the network physics underneath.
Read article →Context Window vs Attention Window: What AI Architects Must Understand
· 5 min read
Context size is not the same as attention behavior. A practical guide for LLM architecture, RAG design, and long-context system trade-offs.
Read article →Recursive Language Models: Why Smarter Navigation Beats Bigger Memory
· 8 min read
RLMs solve the context window problem by letting AI write code to explore information. The result? Tasks going from 0% to 91% success. Here's how it works and when to use it.
Read article →Decentralized AI Compute: Building DePIN Networks with AI Agents and Blockchain
· 11 min read
How AI agents optimize compute allocation while blockchain ensures accountability. A practical guide to building DePIN networks that keep intelligence off-chain and trust on-chain.
Read article →Before You Build: A Realistic Framework for Evaluating AI Use Cases
· 15 min read
Why 80% of AI projects fail and how to avoid being one of them. A practitioner's framework for evaluating AI use cases before you write a single line of code.
Read article →