TEDWARD.NET · A WEEKLY DEV BLOG BY TED WARD
Dispatches from the sharp end of AI & software.
SHOWING 7 / 57 DISPATCHES — TOPIC: AI/ML
ALL 57 POSTS ↗
From Dashboard to Dispatch: Redesigning tedward.net
After a year of 'temporary' design, tedward.net has been completely rebuilt from the ground up. This redesign moves away from the static dashboard model to an editorial-first platform that reflects my weekly focus on AI engineering.
The Foundry Update: Architecting Multi-Agent Intelligence
After a total overhaul of The Foundry, I am shifting my strategy. By focusing on granular model selection and graph-based codebase management, I am prioritising organic adoption over a premature public release.
Knowing When to Fold: Why I'm Shutting Down Vyzo
Shutting down a project is never easy, but it is a vital part of the development lifecycle. Today I am reflecting on why I am sunsetting Vyzo, from the challenges of platform monopolies to the harsh economics of LLM API costs.
Building the Ultimate Local-Only AI Swarm: From Pomodoro Apps to Polyglot WebAssembly
I have built an autonomous, self-healing AI swarm named The Foundry that operates entirely on local hardware. Now, I am putting it through a brutal 10-step polyglot gauntlet to see if it can master everything from React frontends to C++ and WebAssembly.
Confession: I Hated TDD. Then I Learned How to Make AI Do It.
I used to treat TDD like a chore, but AI has transformed it into my most powerful development tool. By delegating the heavy lifting of test-writing to LLMs, I have reclaimed my role as an architect rather than a code-babysitter.
The Sovereign Swarm: Engineering Your Own KnowQL with Blue Brain Nexus
Traditional RAG is failing autonomous agents. Learn how to bypass proprietary SaaS lock-in by engineering a deterministic, graph-based knowledge engine using Blue Brain Nexus and custom declarative queries.
Mac vs PC: Choosing the Best Laptop Architecture for Local LLM Development
Choosing between a Mac and a PC for running local LLMs is a pivotal decision for any AI engineer. We explore the architectural differences between Apple's Unified Memory and NVIDIA's CUDA to help you decide which hardware best suits your development workflow.