Ben Welsh

aiglossary.news A glossary of AI terms for journalists

For our #NICAR26 panel we threw together this free, open-source glossary of AI terms and foundational concepts that journalists should know.

We will be adding to this! (Forked from prior work by @palewi.re @dwillis.bsky.social et al)

aiglossary.news

If you want to talk tech, let's get the comments kicking. We haven't published the code that powers the site, but I'm eager to share the new techniques I learned putting it together.

For the nerds in the room, the backend is a Qdrant vector database harnessed by Python's FastAPI. Users tap into it via Svelte, the Node.js framework invented at The Guardian.

This is an early release and a work in progress. If you encounter bugs, please report them to help@ire.org. Here's what we have planned for the month ahead.

Access is restricted to active IRE members, authenticated through the recently relaunched ire.org. If you're not a member or let your card lapse, this is a great reason to get out the credit card.

This is the result of a team effort by a committee of volunteers, with the development led by me, Derek Willis and Cody Winchester.

It will also automatically recommend entries similar to your search.

The site, which launched today at #NICAR26, is powered by semantic search technology. That means it will use AI to match results based on the meaning of your words, not just exact keyword hits.

That includes thousands of tip sheets, training materials, conference recordings, slide decks and contest entries.

It indexes more than 33,000 resources journalists have contributed over the decades.

🔍 I'm pleased to announce the launch of archive.ire.org, a new AI-powered search engine unlocking the collective knowledge of Investigative Reporters and Editors members.

A woman is holding a baby alligator. She has a leather purse and gloves which may be made of alligator skin.

Woman with baby alligator https://tessa.lapl.org/cdm/ref/collection/photos/id/108690

🧐 https://www.reuters.com/world/china/global-markets-global-markets-2026-03-04/

RE: https://mastodon.palewi.re/@palewire/116000811728539952

Week 5's script, on how to load data into your Svelte components, is now unlocked and free for anyone to follow along. https://palewi.re/docs/coding-the-news/scripts/week-5/

🧐 https://www.reuters.com/world/china/global-markets-global-markets-2026-03-01/

🧐 https://www.reuters.com/world/us/just-one-four-americans-support-us-strikes-iran-reutersipsos-poll-finds-2026-03-01/

🧐 https://www.reuters.com/world/most-americans-back-trumps-deportation-goals-not-his-tactics-reutersipsos-poll-2026-02-26/

RE: https://mastodon.palewi.re/@palewire/116119773803070204

"First LLM Classifier" is soooold out! #NICAR26 is ready to rip.

Fret not. You can still hit the wait list. And we will be releasing an online textbook with the full script for anyone to play at home.

🧐 https://www.reuters.com/world/asia-pacific/nvidia-forecasts-first-quarter-sales-above-estimates-2026-02-25/

RE: https://mastodon.palewi.re/@palewire/116000811728539952

Week 4's script, on how to introduce interactive features with Svelte, is now unlocked and free for anyone to follow along.

https://palewi.re/docs/coding-the-news/scripts/week-4/

Dedicated To You John Coltrane, Johnny Hartman · John Coltrane And Johnny Hartman · Song · 1963

🔊 https://open.spotify.com/track/7981FAW8DbDs1ueK4Ha8R2?si=u5OblCwCSy24dEC3ApN2ag

🎁 Finally, Derek Willis and I will unveil something new we've made for IRE members. I'm ooking forward to sharing more soon. The unveiling is Thursday at 2:30. https://schedules.ire.org/nicar-2026/#/session/1234

We'll teach you how to convert massive shapefiles to the compact PMTiles format, and then display the tiles on an interactive map using a data-driven style.

🌎 𝗙𝗶𝗿𝘀𝘁 𝗣𝗠𝗧𝗶𝗹𝗲𝘀 𝗠𝗮𝗽, taught with Jon Schleuss, will show how to display a massive dataset on an interactive map using Protomaps and MapLibre. https://schedules.ire.org/nicar-2026/#/session/1303

We'll teach you how to submit dozens of prompts at once as part of an automated routine, and then evaluate and improve results using a rigorous, scientific approach.

🏷️ 𝗙𝗶𝗿𝘀𝘁 𝗟𝗟𝗠 𝗖𝗹𝗮𝘀𝘀𝗶𝗳𝗲𝗿, taught with Andrew Briz, will show how journalists use large-language models to organize and analyze mammoth datasets. https://schedules.ire.org/nicar-2026/#/session/1274

📣 This year I'll be leading two hands-on training courses at Investigative Reporters and Editors' annual data journalism conference in Indianapolis. Here's what I'll be up to.

🔊 https://lakeciabenjamin.bandcamp.com/track/om-shanti-feat-georgia-anne-muldrow-and-meshell-ndegeocello

🧐 https://www.reuters.com/business/buy-america-bye-america-wall-street-exodus-gathers-pace-2026-02-20/

🧐 https://www.reuters.com/world/us/scotus-live-us-supreme-court-rules-legality-trumps-tariffs-2026-02-20/