Family history and AI-friendly software

Nate Meyvis launched TurboTree, a Web service that lets users query family history data through an API with AI assistance, after finding that LLMs excel at retrieving and tracking real-world information. The site, built in about three hours, allows users to ask any LLM with an API key arbitrary questions about their family history, and Meyvis emphasizes the value of human-LLM teamwork in genealogy research.

Here are two subjects that have been on my mind: 1. New models are vastly better at retrieving and tracking lots of real-world information, as I've discussed here https://www.natemeyvis.com/some-recent-applications-of-ai/ and here https://www.natemeyvis.com/civic-applications-of-generative-ai/ . 2. API design will need to change in a generative-AI world see here https://www.natemeyvis.com/spaced-repetition-apis-and-generative-ai/ and here https://www.natemeyvis.com/a-first-guide-to-building-apis-with-ai/ . 3. There's enormous power in "Wiggumizing" core processes: make them amenable to improvement by means of instructions that can be grasped by an LLM statelessly or near-statelessly. Context management is still important https://www.natemeyvis.com/thinking-about-context/ that post is almost 7 months old but still at least slightly relevant , and a Wiggumized process automates much of the context-management problem away. Researching family history is a good example of a domain that ought to be newly amenable to AI assistance: there's a ton of information available, and the more that LLMs can juggle lots of practical information, the better they ought to be at it. So, I've been experimenting with a Wiggumized, API-first, AI-first family history research process. It's been illuminating: 1. There's even way more data out there than I suspected. It turns out that I had ancestors in modern-day Belgium when it was part of France during the Revolution, and I found documents officially dated with the revolutionaary calendar https://en.wikipedia.org/wiki/French Republican calendar . 2. I'm even more convinced of the power of exposing a robust API and telling AI how to use it: for now, at least, I can use different models and a variety of computer resources much more flexibly as an API consumer than I can make programmatically available through a Web service. 3. Family history is a great example of a domain where human-LLM teamwork producing much better results than either humans or LLMs can get individually. Some of this is that humans can help LLMs avoid and correct silly mistakes, can tell family history to LLMs, can help choose between lines of research, and so on. Some of it is just that humans are allowed to look at Web sites that bots are not allowed to look at, so it's useful to have a system where the LLM can ask the human to help out with data retrieval. 4. If you have a lot of practice https://www.natemeyvis.com/humane-adaptive-ai-bootstrapping/ in turning one-off projects into at least minimally productionized services, the productionization process is by now very fast. I find that it's often worth it even for the sake of keeping myself honest or showing it to a single other person. 5. However much I remind myself to be ambitious about trying things with AI, I don't seem to do it enough. I'm not surprised that it wasn't hard to add a mapping feature to a site like this, but the fact that it would have been time-consuming five years ago added some mental friction. 6. Simply having a bunch of information I care about available via API is very useful: I can now ask any LLM with my API key arbitrary questions about my family history. 7. Vercel is very impressive. The result: TurboTree https://turbotree.org is a site where you can set your LLMs on their merry, Wiggum-y way. This is about as polished as you'd expect a three-hour-old Web service to be, and I make no guarantees about how well it works, but I do plan to keep it up and running for my own use. Bug reports are very much appreciated You'll probably be correcting AI mistakes, and I'd be grateful if you'd also take a second to help me correct mine.