TEDWARD.NET · A WEEKLY DEV BLOG BY TED WARD
Dispatches from the sharp end of AI & software.
SHOWING 7 / 63 DISPATCHES — TOPIC: LLM
ALL 63 POSTS ↗
Taming the Slop: How I Ship Multi-Month Features in a Week with Agent Loops
Tired of AI generating unmaintainable code slop? Discover how orchestrating 8 to 12 concurrent Claude and Codex loops with spec-driven development allowed me to ship a multi-month feature in just one week.
The Great Context Trap: Why Your AI Memory is Broken (And How to Fix It)
We are bleeding our project context to cloud providers every time we open a new chat window. Discover how the Foundry ecosystem and the Model Context Protocol enable portable, sovereign AI memory that finally puts you back in control.
The Next AI Battlefield Isn't Intelligence. It's TPS.
The era of chasing 'smarter' AI is over. As foundational models hit the point of diminishing returns, the real competitive advantage has shifted to high-speed inference and semantic governance.
The Expert's Trap: Why Seniority is Stalling AI Adoption
Deep seniority in traditional coding is becoming a barrier to AI innovation. While many veterans use AI merely for boilerplate, non-traditional developers are building agentic systems by rethinking the very nature of software orchestration.
The AI API Trap: Why Enterprises Will Pivot to On-Prem, Specialised Models
The enterprise AI honeymoon is ending. As token costs spiral and vendor lock-in tightens, companies are turning to on-premise Small Language Models to regain control, security, and cost efficiency.