Extend and Improve: The Design You Already Have Is the Job
New code is cheap to draft. The lasting move is older: add to a design someone still understands, or tidy that design until the next change is easy.
18 min read
← All topics
AI
A topic hub collecting every article tagged AI. Use it to explore related posts and follow this theme across the site.
33 articles
Explore More Topics
Your AI Assistant Might Be Cheating on Its Homework
Researchers gave AI agents hard assignments — with the answers secretly left lying around. Every AI peeked. Here is what that means for you, and 5 simple habits that keep you in control.
10 min read
What Is an AI-Native App? A Working Definition, Architecture, and Practical Test
AI-native apps are not ChatGPT wrappers. They are systems where model inference, retrieval, memory, orchestration, tools, and evaluation are core infrastructure. Here is a working definition, the reference architecture, and a test you can apply to your own product.
21 min read
How Long Should an LLM Response Be? Deriving a Length Budget From Human Reading Capacity
Stop arguing about whether AI answers are too long. Human reading and review capacity are measurable, so the ceiling is derivable: 238 words per minute, a time budget per response class, and a token number you can put in a system prompt and an eval.
21 min read
Forward Deployed Engineers: Who Owns the Last Mile of AI?
Forward Deployed Engineers turn AI capabilities into production outcomes. Learn what FDEs own, when the model works, where it breaks, and how to evaluate the role.
21 min read
Is AI Generating a World of Code Slop?
AI code is not inherently bad, but generation is getting cheaper faster than review, verification, and maintenance. Here is what the evidence says and how to measure the risk in your own repositories.
27 min read
Do New Frontier LLMs Really Resolve Ambiguity Better?
Frontier labs increasingly claim their models understand intent with less prompting. Here is what the evidence supports, what training changed, and how to test ask-versus-guess behavior in your own agents.
21 min read
WebAssembly in 2026: What It Means for AI, Vibe Coding, and the Future of the Internet
A source-backed recap of WebAssembly in mid-2026 — Wasm 3.0, the Component Model, WASI 0.3, browser AI inference, and why WASM is the runtime layer behind vibe-coding sandboxes and portable edge software.
15 min read
How Fast Is gpt-oss-120b? Speed, Quality, and Routing Tradeoffs in 2026
For engineers evaluating gpt-oss-120b: OpenAI's open-weight model is fast for an open reasoning checkpoint, but throughput depends heavily on the provider and benchmark view. Here is how to read Artificial Analysis, OpenRouter trends, and the cost tradeoffs behind fast inference.
20 min read
How to Improve LLM Behavior and Personality in 2026: Big Models, Small Models, and Modern Alignment
A source-backed guide for engineers and PMs on shaping model behavior and personality across frontier LLMs and small language models, from prompts and DPO to persona vectors and distillation chains.
21 min read
AI Engineering Human Judgment Code Review Product Management Developer Productivity Loop Engineering
Still Human Work: The Tasks That Need Judgment and Intuition When AI Writes the Code
AI can generate most of the code. It still cannot decide what to build, sense when 'correct-looking' output is quietly wrong, or own the consequences. A field guide to the tasks that stay human — for engineers and PMs.
16 min read
LLM-Based Personalization in 2026: Cheap, Quick, and Efficient
A practical guide for engineers and PMs who want useful LLM personalization without a giant recommender team, expensive fine-tuning program, or fragile memory layer.
15 min read
How AI Helps Engineers Evolve and Scale Modern Apps
AI can help teams move faster, but the real unlock is designing agents, skills, evals, traces, and self-correction loops around your app.
15 min read
Blueprint Over Bytes: How Modern Engineering Shifted From Writing Code to Designing Systems
AI is changing the center of gravity in software engineering: less manual typing, more specification, validation, system design, and human judgment.
9 min read
From Intuition to Metrics: How to Know You're Using AI Correctly
Most AI programs start with intuition and optimism, then hit a harder question: can anyone prove the system is creating value? This guide turns AI adoption into a measurement problem, using baselines, outcome metrics, evals, and learning loops.
15 min read
Claude Sonnet 4.6 1M vs Composer 2.5 Fast: A Practical LLM Comparison
A friendly, evidence-based comparison of Claude Sonnet 4.6 1M and Cursor Composer 2.5 Fast across speed, intelligence, coding, agents, cost, and product fit.
14 min read
Part 2: Alternatives to Claude Opus 4.7 1M for Engineers in 2026
A practical engineering comparison of Claude Opus 4.7 1M alternatives: GPT-5.5, DeepSeek V4 Pro, DeepSeek V4 Flash, Gemini 3.1 Pro, Gemini 3.5 Flash, and Kimi K2.6.
20 min read
1M vs 200K Context Windows: What Actually Changes for LLM Apps
A practical comparison of 1M-token and 200K-token LLM context windows: what gets easier, what still breaks, and how Engineers and PMs should choose an architecture.
18 min read
Self-Modifying Software: From Fixed Points to Hot Patches
Self-modifying software is not science fiction. It sits on deep computability theory and shows up today in JIT compilers, livepatching, dynamic updates, malware, and AI-assisted code loops.
13 min read
How to Read Dense Engineering Articles With AI: From 90-Second Skims to Source-Grounded Deep Dives
A practical workflow for engineers who want to digest long, technical articles without drowning in detail. Start with quick-view prompts, then move into grounded notes, multi-pass summaries, and long-context research workflows.
17 min read
Why We All Suddenly Talk Like AI People
From context and hallucinations to hardening and vibe coding, AI didn't invent all these words, but it definitely gave them a promotion.
7 min read
When Code Gets Cheap, Complexity Moves: Rethinking Estimation in the AI Era
AI makes first-draft code cheaper, but it does not erase ambiguity, integration, verification, coordination, or production risk. That means engineering complexity has to be discussed differently, especially in Scrum planning.
16 min read
AI Work Paradoxes: Why Faster Tools Are Making Professional Life Feel Heavier
The emerging AI-era problem is not just automation or job loss. It is possibility overload, expectation creep, verification fatigue, boundary collapse, and work that expands faster than human attention.
12 min read
Why Concise AI Responses Work Better: Evidence, Biases, and a Better Default for Engineers and PMs
The strongest evidence does not say 'always write less.' It says humans do better with lower cognitive load, clearer cues, and progressive disclosure. Here's how that changes how we should generate AI responses and reports.
11 min read
How to Review AI-Generated Responses: A Practical Rubric for Engineers and PMs
A practical, source-backed workflow for reviewing AI-generated responses for factual accuracy and relevance, scoring them with structured rubrics, and turning feedback into better prompts, evals, and product decisions.
15 min read
AI Agents as Research Tools: From Curiosity to Prototype in Hours
How AI agents are collapsing the gap between 'I wonder how X works' and 'I have a working implementation of X' — and the research workflows that actually hold up under pressure.
10 min read
AI Planning Tools for Product Development: Claude Code, Cursor, and Beads
A research-checked comparison of Claude Code, Cursor, and Beads for planning, execution, persistence, and async collaboration in modern product development.
23 min read
The Chat Pivot: Why Web Apps Are Replacing Menus with Conversations
From Cloudflare's Cloudy agent to GitHub Copilot in your issue tracker, the web is shifting toward conversational interfaces. Here's what's driving it, who's doing it right, and what security challenges remain.
9 min read
Less Code, Less Hallucination: Why AI Co-Generation Demands Simpler Frontends
When an AI agent spins up tasks on a complex frontend, complexity becomes the enemy. The hypothesis: simpler codebases mean fewer bugs — and in the age of AI co-generation, fewer hallucinations too.
12 min read
How AI Is Reshaping Engineering: The Shift From Code to Product
AI isn't just making engineers faster — it's changing what engineering means. Here's what that shift looks like, and why the best days for software teams are still ahead.
7 min read
Building Roblox Games with AI Using MCP
Learn how to connect Claude Code to Roblox Studio via MCP and go from spawning your first part to automating full game systems — with practical examples at every level.
8 min read
How to Create Your Vibe Coding App
A practical guide to building and shipping a full-stack app using Lovable for UI, Claude Code for logic, and Cloudflare for deployment.
5 min read
How to Improve Code Quality During Vibe Coding
Vibe coding is fast, but speed without discipline creates debt. Here's how to keep your AI-generated code clean, tested, and maintainable.
13 min read