Ep 41 is live: "More Is Not the Same as Better"
400x more DNA data. 2.3M searchable pension pages. Wikipedia bans AI content 44-2. And an interview with FamilyTreeDNA's David Vance that's one of the best we've done this year.
podcast.show/3738800/epis...
Posts by Steve Little
In 2023, AI could handle a 4-minute task. By 2026, 12 hours. That's the METR time-horizon benchmark — and the curve is nearly vertical. One metric, not the whole story, but hard to look away from. And new models coming soon.
The Genealogical Research Assistant. Applies the Genealogical Proof Standard to any AI tool. Refuses to fabricate. Classifies every fact individually. Protects living people.
Works in ChatGPT, Gemini, Claude, and local models. Creative Commons.
Fair warning: "I built a thing" post incoming.
18 months. A free prompt that teaches AI the difference between "primary source" (wrong) and "original source containing primary information" (genealogy).
Full post with the analysis, the contradiction moment, and instructions to try it yourself: vibegenealogy.ai/p/turn-anyth...
The prompt is free on GitHub and works in ChatGPT, Claude, any chat-based AI; the "skill" version works with Claude Code, Claude Cowork, Codex, OpenClaw, or any agent harness.
Friend asked if anyone had a tool to turn any file into a GEDCOM file. Built one in a couple of hours. Tested it on a 1909 newspaper article -- both Claude and ChatGPT caught a contradictory marriage date I hadn't noticed. Free prompt, works in any chatbot or as a skill in agent harnesses!
Virtus "No Kings" image available in portrait, landscape, square, and banner sizes: jstephenlittlejr.wordpress.com/2026/03/22/s...
Download this Virginia seal “No Kings” image in multiple sizes and aspect ratios—square, portrait, landscape, and Facebook banner—and read the full story behind it and the March 28, 2026, rally at (link in first comment):
Witherspoon is also my first cousin eight-times removed, that is, his grandparents are two of my direct ancestors.
Full statement:
jstephenlittlejr.wordpress.com/2026/03/22/s...
#genealogy
Virginia put the answer on its state seal in 1776: Virtus standing
over a fallen tyrant, his crown in the dust, his chain broken.
Sic Semper Tyrannis. Thus always to tyrants.
This isn't politics. This is inheritance.
March 28. #NoKings
Fun Prompt Friday: I ran a 108-line image analysis prompt on the same family photo across four AI models. Claude, GPT-5.4, Gemini, Grok — scored head to head. Free prompt, full comparison matrix, and the results are not what I expected. #genealogy
Ten days.
The president's counterterrorism director quit, saying this war was started under foreign pressure. Courts ordered Voice of America restored. Thirteen Americans dead, no congressional vote.
Now is the time for all patriots to come to the aid of their country.
Thirteen days.
Now is the time for all patriots to come to the aid of their country.
I made a quiz that maps you onto a spectrum of 34 real AI thinkers. Takes two minutes. You get a personalized report — allies, blind spots, tensions, reading list.
Then I wrote about why genealogists should be building their own tools, not buying them. And five examples to try today.
Link below.
Read it here: vibegenealogy.ai/p/five-thing...
Level I starts March 17. ROOTSTECH15OFF = 15% off ($212 instead of $249).
tixoom.app/fhaishow/1ycwuhd5
Just published my RootsTech 2026 takeaways. Five things that stood out — including why Alton Brown's "uni-tasker" rule applies to AI genealogy apps.
Also: I'm more direct than usual about our Academy course. Fair warning.
Link in reply.
Register at tixoom.app/fhaishow/1ycwuhd5
Use ROOTSTECH15OFF for 15% off ($212 instead of $249)
Tuesdays 1-3 PM ET. Recordings included for 60 days.
Fresh off RootsTech 2026 — Mark Thompson and I taught six sessions on AI and genealogy.
Now we're teaching a 5-week Level I course starting March 17. Practical AI skills + a community that lasts. Recordings available 60 days.
15% off: ROOTSTECH15OFF
Link in reply.
UPDATE: Sam Altman says OpenAI draws the same red lines as Anthropic: no AI for mass surveillance or autonomous weapons. But he still wants a Pentagon deal. Employees at OpenAI and Google signed a joint letter backing Anthropic's stance. www.axios.com/2026/02/27/a...
Claude is already embedded in classified military networks. The standoff raises a core question: who sets ethical limits on AI in war—the companies that build it or the government that wields it?
substack.com/@digitalarch...
Anthropic CEO draws two red lines with the Pentagon: no mass domestic surveillance, no fully autonomous weapons. The Dept. of War threatens retaliation—supply chain blacklist, Defense Production Act. Anthropic won't budge. This may define how military AI is governed for years.
Claude's Custom Skills can turn a genealogy research-log spreadsheet into a footnoted research report. Set up a reusable skill with one prompt, upload your CSV/XLSX, and get polished prose — far faster than the chain-of-thought method from a year ago. familylocket.com/from-spreads...
Claude Skills are the next iteration or evolution of prompt-based genealogy work. Nicole Dyer is a Jedi Master of explaining this technology in a genealogical context.
Loathsome Jargon #3: We traced "hard take-off" from a 1965 math paper to this month's AI panic. Every source named. Every claim traceable. The genealogist's method, applied.
vibegenealogy.ai/p/loathsome-...
A karaoke company erased $17.4 billion from the stock market. Look at this chart — AI capability just went vertical. "Hard take-off" is the scariest term in AI right now, and your feeds are full of it. Here's what it actually means and who's saying it.
Maybe stack or wrap the OCR/HTR prompt with this one, a project I've been helping the IAJGS for about 18 months:
github.com/DigitalArchi...
I'd be interested if this prompt with Gemini 3 Pro yields better results. (I was with LVA's Digital Library Program in the late 1990s/early 2000s, working out an annex in the Portsmouth Public Library, digitizing local library historical photograph collections.)
github.com/DigitalArchi...