Designing for LLMs - Designing for Imperfection

Harnessing Imperfection in LLM-based Design

When do we need human-like intelligence?

Fearmongers and fanboys flag AI’s potential to automate tasks currently requiring human intervention.

The paradox of technology

How simplicity and complexity collide.

Speed of Feedback: How can we keep our users engaged, if the AI keeps them waiting?

The Doherty threshold: only sub-seconds count.

Inattention Valley: The Relationship Between Accuracy and Supervision

The interplay between the accuracy of artificial intelligence and the human need for vigilance emerges as a critical challenge, with implications for safety and decision-making.

The Scale of Human-AI Interaction: What's the Right Level of Control?

The levels of control for AI and the user

How will ChatGPT be remembered?

Embracing the Unpredictable: ChatGPT's Quirks might have the biggest impact in shaping the AI landscape

Integrating the Human: Look Beyond the Algorithm's Plate — Get to Context

Empowering AI through Users: Shaping AI's Trajectory Through Collaboration

Dancing with the Algorithm: Striking the Balance between Trust and Control in AI Adoption

Examining the Factors that Erode User Confidence and Engagement

Scopes and Modes: A System Approach to Building Software

Visibility in AI: Don't Blindfold Your Users

If you do not have all the information the system has, you do not feel in control.

The Broken-Leg Problem: Why Users Hesitate to Trust AI Systems

Understanding the Psychological Barrier to Accepting Machine Learning Predictions