One of the reasons I’m not a big fan of AI search is that it doesn’t seem granular enough to me. That is to say, there’s not a lot of back-and-forth, patron interview type stuff so the AI is left to do a substantial amount of heavy lifting in the form of inferring all the […]
SearchTweaks.com Updated
I’m getting everything ready for my APRA Wisconsin presentation on Wednesday, where I’ll be discussing how to use three of my web sites — SearchTweaks.com, WikiTwister.com, and MegaGladys.com . To that end I spent this morning updating SearchTweaks, changing some things around and killing some bugs. Unfortunately the local news search is going to stay […]
Wikipedia Articles As Containers Holding Intra-Wiki Link Elements: Turning Those Into Search Queries
My thinking about Web search and making the most useful query possible has focused a lot recently on the idea of query-as-cloud-of-topics; instead of thinking about George Washington as a singular search terms you might think of him as a structure encompassing every possible way you can contextually describe George Washington – dentures, cherry trees, […]
Creating Four-Dimensional Search Queries
The silver lining to the cloud of increasing search awfulness is that it’s forced me to think deeply about what search queries are. This has lead me to consider the idea of topical knowledge as an atomistic concept, an ever-shifting cloud of ideas attached to a central notion. The central notion can be as general […]
Searching in Data Tide Pools Before Braving Google’s Oceans
I’ve been playing with the idea of building a little wading pool of data that offers a limited but reasonably authoritative collection of information (in this case Wikipedia), and then exploring the relationships between those data to build more complex search engine queries that are less likely to get snared by junk Google results. I made […]
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 […]
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 […]
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 […]
Remaking Google Uncle Sam (Sort Of) With Mojeek and a CISA Dataset
Do you remember Google Uncle Sam? I can’t blame you if you don’t; Google killed it off in 2011. It was a specialty search offering of Google’s that restricted its results to .gov sites. Very useful! There was a lot of grumbling after it was shut down; in fact, I made a replacement in 2012 […]