If I gave you a list of twenty people from Wikipedia and told you to list them in order of cultural prominence without consulting an external reference, how would you do it? You’d probably start by identifying people you know. You’d use your knowledge to sort them as best you could. But what about the […]
Shaking Wikipedia Categories to See What Pops Up
I’ve been spending the last few days playing with my favorite mental chew toy, the question “How do you ask for what you don’t know?” It’s an important question because every search engine query above a certain level of complexity involves filling in a knowledge gap. How you understand, define, and contextualize that gap means […]
Making Location-Based Timelines With Wikipedia, Wikidata, and Mojeek
I started learning JavaScript in Mayish 2022. I wanted to make tools to address some of the things I disliked about Google search, and after looking around it seemed like JavaScript was the best solution. So I signed up for a course, thrashed and flailed my way through 50 of the 59 lessons, and then […]
Keep An Eye on the Fediverse With the Mastodon Hashtag Monitor
Over 15 years ago I wrote a book called Information Trapping. It was about how to set up online monitors to find online information around certain keywords and keep it coming as a flow to you via tools like RSS, page monitors, etc. As you might imagine, Information Trapping’s resources and tool listings are very […]
Using ChatGPT to Double-Distill Mojeek Results into a Date-Based Topic Overview
My concern about AI-assisted search results has been, from the beginning, the lack of human context. A simple query is rarely going to be sufficient in itself; after all, the user is searching because of some existing information lack. Outside of the most basic queries (When is a movie playing? Where is that restaurant? How […]
Evaluating ChatGPT’s Knowledge Based On Year of Source Data
I’ve been talking to myself in JavaScript about Google’s terrible AI results and why it’s so difficult to have AI turn scraped web into useful search results. I made a thing that does a Mojeek search and restricts results to a specific year via url pattern matching/result filtering. It then retrieves and bundles the filtered […]
Nosy Raleigh v2 Now Available!
I am very pleased to announce that V2 of Nosy Raleigh is now available! Nosy Raleigh uses Open Data Raleigh datasets to map news and happenings in Raleigh, North Carolina, as well as provide information on local news and local government Twitter feeds. It’s available, free and free of ads, at https://www.nosyraleigh.com/ . Let me […]
Turning Raleigh Trees into Hyperlocal News Reporters
I’m having so much fun playing with Raleigh’s tree dataset and giving the trees something to say. Today I gave the trees some hyperlocal news mojo. How it works: when you ask a tree for local news, the program checks to find streets nearby. It then uses a news API to check WRAL, WTVD, and […]
I Talk to the Treeeeessss… with a ChatGPT API Call
I’ve learned enough since last October that I can revisit my project of having Raleigh’s trees act as tour guides for surrounding areas. The city of Raleigh offers an open dataset of city trees. Not every last tree in the city, of course, mostly trees on city property. My old program searched the tree database, […]
AI Is Better With Human Attention As Search Context
Human attention as context for Internet search is immensely powerful. Having an understanding of WHEN a topic was of particular interest allows you to create date-bounded searches that provide more information-rich results and less junk. Which is why it drives me absolutely bonkers that we have a gold mine of human attention records in the […]