Tag: Design & Media

Browse our exclusive articles!

Planning SVG Metaphors: How to Turn an Abstract Concept Into a Hero Image

Visual Computing Bosonica Bosonica -
With a diffusion model you plan the prompt. With hand-drawn SVG there is no prompt - the planning moves earlier, into the metaphor itself.

Multi-AI Orchestration: One Agent Conducting Another

Visual Computing Bosonica Bosonica -
The gains at scale do not come from a better model. They come from a better division of labor between the models you already have.

How to Generate SVG Hero Images with Claude Code

Visual Computing Bosonica Bosonica -
For concepts and hard science, a hand-drawn vector beats a diffusion model on cost, consistency, and safety. Here is the exact method.

Vector vs Diffusion: Why Scaling AI Images Needs Two Engines

Visual Computing Bosonica Bosonica -
Pick one image generator for tens of thousands of pages and you pay in money, months, or quality. The fix is to stop choosing.

AI Image Generation Best Practices for Editorial Work

Visual Computing Bosonica Bosonica -
The techniques we use to produce clean, conceptual, text-free illustrations - shown with one real course rendered five different ways, each next to the exact prompt.
123Page 2 of 3

Popular

Many-to-One: Why a Mapping Backlog Outgrows Its Target Taxonomy

Knowledge Systems 0
You're mapping a messy source vocabulary onto a clean target taxonomy. The target has about 5,600 slots, so the job must be roughly 5,600 decisions — right? The backlog is already past 8,900, and still climbing.

The Fix That Didn’t Take: When a Content-Hash Gate Skips Your Code Change

Developer Operations 0
You shipped a fix to how one field is computed, re-ran the pipeline across everything, and it reported a clean run. Then the consistency check still flags those records as wrong. The fix is in the code, the rebuild "ran" — and the records never changed. Your own optimisation skipped them.

Your Dedup Scan Is Over-Counting — Because It Forgot What You Already Fixed

Developer Operations 0
The report said 80 duplicate groups still to resolve. You'd been resolving them for days. You run it again after a big batch and it *still* says 80-ish. The backlog isn't stubborn — the scan is counting work you already finished.

When Your Skills Folder Is a Deploy Target, Not a Drawer

Developer Operations 0
You hardened a skill in the repo, shipped the PR, and the agent kept loading the old one. Or you fixed the live skill by hand, and the versioned copy quietly stayed behind. Same root cause: the copy you run and the copy you version are two different files.

Subscribe