If stacked small classifiers can outscore prompting a model for aesthetic judgment, that is a reusable technique for teams trying to make AI-generated design measurably less generic instead of relying on vibes.

• 0:00Taste Labs, and slop as the enemy
• 1:33Where design gets objective and where it does not
• 2:53Greatness, and why slop is easier to define
• 3:46Generation costs nothing, taste takes a lifetime
• 5:07Three signatures of slop
• 6:28Two million websites, and what they showed
• 7:48Probes, small classifiers that predict slop
• 10:31Going out of distribution on purpose
• 11:51Turning a brand into something an agent can follow

• videoGenerative UI... in Python? — Jeremiah Lowin, Prefect
• videoThe Design-Code Roundtrip That Isn't — Jonathan Gordon, ReWeaver AI
• videoDesign at the Speed of Adjectives — Paul Bakaus, Renaissance Geek, Inc.
• videoMousepower: agents that can’t be measured, can’t be managed. — Maximillian Piras, Yutori

• videoEnding AI Slop — Thais Castello Branco, Taste LabsAI Engineer
• videoThe Signal Layer: What to Build When Anything Can Be Built — Lena Hall, AkamaiAI Engineer
• videoThe Missing Layer: Design Taste in AI Agents — Hassan El Mghari, Together AIAI Engineer

Checking sign-in…

Loading comments…