Week 10: AI Design Patterns

• Temperature

  • Temperature is the measure of entropy or chaos in generated output

• Nucleus Sampling (top_p = 0.3 / 0.7 / 100

  • Top_p is a parameter that allows us to control the range of tokens considered by the AI model, based on their probability.

    • Smashing Magazine:

      • High temperature + low top_p (poetry, music, ideation, writing)

        Creative accuracy: common words put in unpredictable ways.

      • Low temperature + high top_p (legal docs, medical diagnosis, analysis)

        Predictable precision: rich vocabulary, high clarity

      • High temperature + high top_p (art, innovation, advertising)

        Unpredictable chaos: unexpected results and combinations

      • Low temperature + low top_p (fact checking, analysis, dataviz)

        Predictable order: deterministic, simple, predictable.

    • OpenAI: https://community.openai.com/t/cheat-sheet-mastering-temperature-and-top-p-in-chatgpt-api/172683

• Tokens

• Place Instructions Last

• Go Meta

• AI Fatigue / Quiet AI

Patterns

• Shape of AI

  • Follow up

  • Nudges

  • Suggestions

  • Templates

  • Auto-Fill

  • Summary

  • Token Layering

  • Filters

  • Footprints & Prompt Transparency

  • Inpaiting

  • Parameters

  • References & Citations

  • Workflows

  • Controls

  • Rating

  • Color Scheme

  • Symbols

  • Fine-tuning & Versioning

  • Human Verified badges

Courses

• Smashing Magazine - Design Patterns for AI Interfaces

• Ioana Teleanu - AI for Designers

Newsletters

• AI Goodies

• What I learned

Youtube

• AI Advantage

Other

• Google Prompt Engineering Whitepaper

• Microsoft Generative AI for Beginners

Tools

• Cursor

• Bolt

• V0

• ChatGPT

• Grok

• Claude

• Perplexity

• Copilot

• DeepSeek

• Suno App

• RunawayML

• Midjourney

• Strawberry

• Krea

• Manus

• Replit

• Lovable

• UX Pilot

• Polymet