All articles

64 published

A bold vintage screen-print illustration in cream, slate blue and rust orange of three identical app-screen windows, each marked with the same checkmark seal.

Product Design

AI Models Beat Humans on the Design Brief, and Their Screens Look Alike

An 8 October 2026 benchmark of 15 AI models found all passed over 90% of brief criteria, yet their UI designs resembled each other more than human work. Brief-based review cannot see that.

A bold vintage screen-print illustration in cream, olive green and brick red of a printed code listing with a large red checkmark and a round approval stamp.

Development

AI Code Reviewers Can Coach Attackers to Approval

A 4 October 2026 paper shows an AI pull-request reviewer's own comments guide an attacker to approval with the exploit intact, just as GitHub makes Copilot's approval count.

A bold vintage screen-print illustration in deep green-teal, mustard and salmon-cream of a large magnifying glass over a paper checklist with tick-boxes.

Development

Developers Trust AI When It's Easy to Check, and Code That Runs Passes

Stack Overflow's 2026 survey shows developers trust AI only when they can easily validate it. Three September studies suggest the easiest check, running the code, misses what AI gets wrong.

A bold vintage screen-print illustration in pale sage, deep ink blue and vermilion of a large rubber approval stamp pressing a checkmark mark onto a form sheet.

Creative Tooling

Claude Code Mods Can Approve Commands Before the Classifier Sees Them

Anthropic's new Claude Code mods can approve a tool call after rules and hooks decide, skipping the auto-mode classifier. The real safety layer is now plugin vetting, and solo developers carry it.

A bold vintage screen-print illustration in cream, dusty plum and mustard of a large parking meter beside a wastepaper basket full of crumpled paper, with translucent sketch sheets behind.

Creative Tooling

Figma's Agent Goes on the Meter, and Discarded Drafts Pay the Bill

From 6 October 2026 the Figma agent draws AI credits it can't price in advance and never refunds on undo. That bills hardest for the throwaway drafts it was sold to produce.

A bold vintage screen-print illustration in cream, slate indigo and rust red of a large geometric padlock with a blank sticky note on its body and a small key lying out of reach beside it.

Development

MCP Error Messages Written for Humans Hurt the Smartest Agents Most

A 28 September 2026 preprint finds MCP servers' developer-facing error steps make capable agents fail more, and that naming a server tool in the step fixes it.

A bold vintage screen-print illustration in cream, deep teal and ochre of a bulletin board with two paper printouts, a before and an after sheet, each held by a round push pin.

Development

PixelLeak: The Screenshot Request That Leaked Internal UIs

Glow's PixelLeak report found 13,000+ internal screenshots in public GitHub repos. The cause was a routine review request, and the fix sits in your agent's skill files.

A bold vintage screen-print illustration in deep forest green and pale blush of a large geometric refreshable braille display with braille cells above a row of square keys, in front of a form field and a large circle.

Design Engineering

USWDS Wants AI to Test Accessibility. Agencies Inherit the Gap

The U.S. Web Design System plans to automate accessibility testing with AI. The manual layer it may replace was checked once upstream, so the work could move to agency teams.

A bold vintage screen-print illustration in cream, muted blue and coral of a large fan of five paint-swatch cards on geometric color blocks.

Prototyping

Google's Vibe-Design Agent Fix Restores Exploration, but Nobody Can Score It

A Google-affiliated team rebuilt exploration inside a commercial vibe-design agent. Offline it broadened output; live, users complained less but corrected more, and exports stayed unproven.

A bold vintage screen-print illustration in mustard yellow, dark charcoal and terracotta of a large faceted wedge of Swiss cheese riddled with holes, surrounded by small pull-request card and checkmark accents.

Design Engineering

37signals' Basecamp 5 Passed Every Pull Request Review, Then Broke

At 37signals, AI-agent pull requests for Basecamp 5 each passed review, but together they wrecked the architecture, exposing who wasn't watching the whole system.

A bold vintage screen-print illustration in cream, deep plum and warm ochre of a large unfinished poster on an easel, its blank rough-edged corner exposed as a geometric orange speech bubble bursts out from behind it.

Product Design

Google's AI Teammate Study Warns Against What Ando Just Launched

Google's five-month study of a proactive AI 'teammate' found unprompted DMs and interruptions broke trust — the exact behaviors Ando's new Slack rival sells as its pitch.

A bold vintage screen-print illustration in cream, sage green and dusty mauve of a large geometric stopwatch, its dial split open to reveal a settings dropdown menu list, poised above a tilted printed reference card.

Product Design

Figma's Own Trial Finds Figma Make Mostly Helps PMs, Barely Designers

Figma's own randomized trial found only a marginal, fragile time saving for designers using Figma Make, versus a robust 35% saving for product managers.