
Development
AGENTS.md Works as a Rulebook and Fails as a Tour
ETH Zurich tested 138 AGENTbench instances plus 300 SWE-bench Lite cases and found AGENTS.md's instructions change agent behavior, but the repo overview doesn't, while adding 20% to run cost.
Read the articleFeatured

Figma's Agent Skills Sell Personalization the Data Doesn't Back
Figma's 13 August skill-authoring launch is pitched on capturing personal taste, but a study three days earlier found generic skills beat personalized ones.
Read the article
AI Images Only Lose Trust Once Someone Suspects They're Fake
Two 21 August 2026 studies find AI images cost nothing until viewers suspect them, just as EU Article 50 makes that disclosure mandatory by default.
Read the articleLatest Articles

Design Engineering
AI Writes Responsive Code That Isn't Responsive
A 12 August 2026 benchmark found 68% of AI-generated webpages break across real browsers and devices, 1.7x the human baseline, while reading fine in a diff.
Read the article
Development
Multi-Agent Coding Teams Don't Need a Boss, a Study Finds
A 1,902-run study of Claude Code agent teams found naming a coordinator adds no measurable benefit, while shared-file versus messaging coordination swings token costs by up to 42%.
Read the article
Prototyping
Design Theater: The Gap Between an AI's Rationale and the Screen
A July 2026 benchmark found over a quarter of AI design tools' stated rationales don't match the interfaces they built, and the gap is worst on behavior, not looks.
Read the article