Summary
Join Savina Hawkins as she presents a focused exploration of large language models in User Experience Research (UXR). This talk zeroes in on practical, actionable strategies for leveraging these advanced AI tools to enhance UXR outcomes. Savina will discuss the dual nature of large language models, illuminating their potential to both revolutionize and challenge UXR practices. Attendees will learn to identify and mitigate risks while maximizing the benefits of these models in real-world scenarios. The session promises a clear, concise roadmap for UX researchers to effectively integrate large language models into their workflow, ensuring positive, impactful results.
Key Insights
-
•
Prompt engineering is emerging as the fifth essential tool for researchers alongside traditional UXR methods.
-
•
Large language models learn language and reasoning skills solely from statistical relationships in massive text data, not human-like understanding.
-
•
GPT’s transformer architecture acts like advanced kitchen technology enabling fast, focused processing of text inputs and outputs.
-
•
Prompt chaining, especially multi-threaded types, allows complex workflows where output from one AI prompt feeds the next, enabling rigorous analysis.
-
•
The art of prompt design parallels crafting research interview guides, utilizing wording, order, context, and priming carefully.
-
•
Current AI, including GPT, can produce convincing but sometimes false or biased outputs, highlighting the risks of blind trust or magic eight ball thinking.
-
•
Future AI advancements aim to achieve artificial general intelligence (AGI), combining learning from experience, problem solving, and contextual understanding.
-
•
Humanistic researchers are uniquely suited to shape ethical AI design through their expertise in mental models, values, and historical context.
-
•
AI-driven transformations will disrupt traditional workflows, power structures, and redefine white-collar roles, demanding dialogue on shared human-technology futures.
-
•
Despite fears of automation, AI tools can democratize access to high-level knowledge work skills, but require critical human interpretation to avoid misuse.
Notable Quotes
"I’m willing to bet that every researcher in this room by the end of 2025 will add prompt engineering to their research skillset."
"GPT is like a master chef who’s traveled the world sampling and learning from every cuisine imaginable."
"Large language models learn spelling, grammar, how to engage in dialogue, how to write many languages, even code, and even how to argue, persuade, and deceive."
"The secret sauce behind GPT’s abilities is the transformer architecture, the latest in kitchen technology that allows the chef to work really fast and efficiently."
"Prompt chaining is one of the most underrated techniques in prompt engineering, turning chains of prompts into designed information processing workflows."
"Prompting at its core involves very specifically using the inputs you give the technology so you can elicit desired outputs."
"The art of prompt design shares a strong connection with the art of conducting interviews and creating discussion guides."
"AI tools can do the entire process of qualitative analysis at the click of a button."
"When humans blindly prompt a large language model, they’re not receiving wisdom from an all-knowing oracle but probabilistic outcomes based on patterns."
"Our roles will evolve into beings that imbue meaning into processed information while AI industrializes content creation."
Or choose a question:
More Videos
"Scale isn’t just about quantity, it’s about the quality and impact you have on the outcomes of the organization."
Standardizing Product Merits for Leaders, Designers, and Everyone
June 15, 2018
"Space has meaning in a map—if you move components around without reason, it’s no longer a map."
Simon WardleyMaps and Topographical Intelligence (Videoconference)
January 31, 2019
"White supremacy is the belief system of the superiority of whiteness that can embed itself in algorithms."
Sandra CamachoCreating More Bias-Proof Designs
January 22, 2025
"We’re all capable of creating and perpetuating toxic work relationships."
Darian DavisLessons from a Toxic Work Relationship
January 8, 2024
"After each interview, I input the transcript into ChatGPT and ask for three key takeaways that I can quickly share with stakeholders."
Fisayo Osilaja[Demo] The AI edge: From researcher to strategist
June 4, 2024
"The seven-foot-wide diagram showed the product’s true complexity, sparking necessary conversations with leadership."
Uday GajendarThe Wicked Craft of Enterprise UX
May 13, 2015
"We formed a small core task force empowered to make decisions to avoid delays from formal reviews."
Davis Neable Guy SegalHow to Drive a Design Project When you Don’t Have a Design Team
June 10, 2021
"We did a great cleanup of patterns from every decade and deleted anything off brand or untested."
Eniola OluwoleLessons From the DesignOps Journey of the World's Largest Travel Site
October 24, 2019
"Design Ops people want to standardize processes and reuse organizational knowledge for clarity and confidence."
Aurobinda Pradhan Shashank DeshpandeIntroduction to Collaborative DesignOps using Cubyts
September 9, 2022
