Are You a Luddite?
Are we focusing on the wrong questions about AI? This post challenges anti-AI sentiment, comparing content saturation to London's 1894 horse manure crisis and arguing for quality over origin.
Blog
Deep dives into AI engineering, LLMs, agentic systems, and building production AI applications
Your Ego Is The Real AI Bottleneck
Challenge the naive claims of AI-driven job obsolescence. This satirical blog post argues AI elevates standards, making genuine expertise in design, product, and engineering more valuable than ever, exposing ego-centric views on 'obsolete' professions.
The Stack Collapse
Explore the evolving UX from User+Machine to pure Machine, the discomfort for enterprises, and the imperative for users to take ownership of powerful AI tools, using real-world examples.
Stop Teaching Horses To Drive Tractors
Why teaching LLMs to use human-centric browsers is a flawed abstraction, akin to horses driving tractors. Explore business logic barriers and advocate for API-driven precision.
The Ghost in the Neural Network
Explore how LLMs harbor emergent strategic behaviors and navigable semantic spaces, moving beyond the 'stochastic parrot' dismissal toward understanding potential functions and guided intelligence.
The Vibe Coding Delusion
Why 'vibe coding' platforms are fundamentally flawed. Discover why a lack of crucial detail, not abstract vision, leads to slop, tech debt, and platform failure in the age of GenAI.
The Death of Intermediate Frameworks
The AI era redefines programming language value. Discover why Python is for experimentation and Rust dominates runtime, as AI's efficiency metrics challenge traditional frameworks like React.
The Agentic Protocol Wars Are Over
The donation of MCP and other projects to the Open Source Agentic Foundation signals an end to protocol fragmentation, ushering in an era of alignment and unified building for the agentic stack.
Stop Building God Agents
Explore why aggressive context curation and agentic mesh architectures are essential for senior AI developers. Debunk 'God agents' and understand how Google's ADK and A2A frameworks enable true agentic flows.
The Cognitive Hollow - Why AI Efficiency Creates Dependency, Not Skill
An analysis of how AI induces cognitive offloading in education, conflating 'doing' with 'understanding', and creating a new class divide between those who wield AI and those replaced by it.
The Great AI Retreat - Why 'Returning to Research' Is an Escape From the Hard Work of Building Products
Explore why the AI industry's pivot to 'fundamental research' is a strategic retreat from the hard realities of productization. This post argues that the future of AI depends on disciplined engineering, not just theoretical breakthroughs.
The Learning Illusion - How We Built a Sophisticated Parrot and Mistook It for a Hawk
Current AI is a sophisticated parrot, not a true learner. Discover why neuro-symbiotic frameworks and growth loops are the real path to adaptive cognition, moving beyond the illusion of deep learning.
The Scaling Arms Race Is Over - The Application Age Has Begun
A deep-dive into why the AI industry is shifting from a focus on scaling foundational models to building value at the application layer, driven by the new realities of cost, speed, and model commoditization.
Building a Non-Worthless MCP Server: Production Architecture Checklist
Most MCP servers are prototypes. Here's the engineering checklist for building production-grade infrastructure.
The MCP Reckoning: Why the Protocol Never Worked and What Comes Next
Anthropic's code execution with MCP isn't innovation. It's an admission the original paradigm was broken. Here's what comes next.
Return of the king: Open AI's Christmas Nightmare
We now have a cheap, fast and highly capable alternative from Google to build agentic flows.
The lie of Agentic Frameworks
A critical analysis of Agentic AI frameworks.
Exploring Built-in AI for Chrome: The Prompt API
Discover Chrome's Built-in AI. This deep dive explores speed, cost, and usability advantages, testing the limits of embedded AI in browsers. Leverage in-browser LLMs for interesting AI solutions.
A forensic analysis of the Claude Sonnet 3.5 system prompt
Claude 3.5 Sonnet artifacts are to structured output such as code generation, what vector retrieval is to rag. It is the search and retrieval system for structured output.
Building a data privacy analyser using AI. Robot eating cookies.
Discover the journey of building a cutting-edge AI data privacy tool with five integrated AI APIs. Explore the challenges, costs, and lessons learned in using AI for advancing data privacy.
Generative AI: Cracking nuts with a sledgehammer
Generative AI is misunderstood as a sentient tool that is capable of expert, highly qualified output. The truth is, Generative AI is capable of performing enormous amounts of work, to an intermediate (at best) level.
AI powered voice chat in June 2024: Lipstick on a pig
I built a simple version of OpenAIs voice functionality, using Groq, Llama3, NextJS, DeepGram, SpeechRecognitionAPI. Talk, listen and converse with LLMs.
Why tyingshoelaces.com?
Chapter one. How did we get here. The beginning of a journey through tech.
The Gladiator meets Silicon Valley
Human nature, large corporations, politics all mixed into a juicy cocktail about the dynamics of power in big tech. With swords.
About Edward Burton
Edward is a full-stack developer and technology leader with 15+ years of experience