Summary
Large Language Models (LLMs) are to language as spreadsheets are to numbers: tools for modeling, exploration, and development. Among their many capabilities, LLMs can alleviate chores related to the design and implementation of information architectures. But doing so requires venturing beyond chat-based interfaces. In this brief demonstration, we'll see how to use OpenAI's API and a few open source command line tools to re-categorize content in a 1,000+ page website. The techniques demonstrated can be extended to other common content organization tasks.
Key Insights
-
•
The discoverability of older content on blogs is often a challenge, making accurate tagging essential.
-
•
LLMs like GPT-4 can significantly reduce the manual workload involved in organizing content.
-
•
A structured approach to task automation can be effectively implemented using a four-step framework.
-
•
Having a clean, obvious taxonomy is crucial for successful AI interaction and content tagging.
-
•
Reviewing AI-generated changes before implementation is necessary to ensure accuracy and relevance.
-
•
AI can provide valuable insights, potentially improving existing classification systems.
-
•
LLMs can function as both a tagging assistant and a surveyor of content relevance.
-
•
Automation can save considerable time and effort, exemplifying the potential of AI in daily tasks.
-
•
This process can be scaled to various content management systems beyond static site generators.
-
•
Engaging with the community for feedback can enhance AI implementation experiences.
Notable Quotes
"I'm an information architect, which means that I organize websites and apps to make stuff easier to find and understand."
"This is a case study on one such toil that I've been removing using LLMs."
"The more recent stuff gets more attention and the older stuff has discoverability problems."
"The first step is gathering the information and the second step is reviewing the changes that the LLM is proposing to make."
"I had to clean this taxonomy up, and I eliminated terms like TAOI."
"GPT actually functioned as an assistant, not just in retagging things, but also in the taxonomy itself."
"It took about three hours from beginning to end to do this, and I was only involved in about two of those hours."
"Be open to contributions; the LLM might help improve your taxonomy."
"I expect that this process is scalable across other systems."
"Good luck as you venture into this wild new world."
More Videos
"You have not lost your rights, you don't lose your humanity."
Sahibzada MayedThe Politics of Radical Research: A Manifesto
March 27, 2023
"You can pull pieces and parts from off-the-shelf models as you need, but only where it makes sense."
Dave HoraAdvice for Establishing Research
December 8, 2022
"Imagine if team members find broken links in your playbook – it erodes trust."
Gabrielle VerderberDocumentation Your Team Will Actually Use
October 3, 2023
"Not every diverse population will have the same experiences; I don't have every black experience."
Raven VealDark Metrics: Illuminating the Negative Impact of Digital Health Design
March 12, 2021
"Prototyping is not just about usability—it's about exploring ideas."
Gretchen AndersonScaling the Human Center
June 8, 2017
"Every time content design gets involved early, the quality and efficiency of the team improves significantly."
Craig Brookes Andreas Huebner Morgan Quinn"Just Make it Look Good" and Other Ways We're Misunderstood
June 11, 2021
"Digitaf changed the way parents experience the early years of their children's childhood."
Sarah AuslanderIncremental Steps to Drive Radical Innovation in Policy Design
November 18, 2022
"The success of any framework is in its ability to scale sustainably."
Joe Meersman Pooria SohiUse AI to Drive Outcomes that Go Beyond the Design Sprint
September 25, 2024
"Inclusive design and research is a process that helps us make our products more inclusive and innovative."
Saara Kamppari-MillerInclusive Design is DesignOps
September 29, 2021
