There's also two other important limitations to using an LLM and just providing it with pairs of records.
It does not know enough about the records in the context of the overall dataset:
- what is the data quality and to what extent do we expect a errors in some fields
- how unusual are certain values such as names in the context of the dataset as a whole, e.g. some names would be very common in some countries but rare in others.
Another great article, thanks. I thought a lot about that too, and basically realized the same thing (this wasn't the coding agent), that frequency in the dataset mattered a lot for how useful a match is, and made frequency lists from my datasets, both on how common the literal names were and the phoneme-reduced names.
But I'm worried about that "bitter lesson" the TypeSafe CEO refers to, and that we're retreading the steps of natural language processing and a lot of other fields, trying to come up with clever rules, when the rule-based approach simply never gets good enough. I need matching to be good, it's absolutely central to genealogy, and I've seen the damage blindly linking by hand-crafted matching formulas can do.
I agree, and I think LLMs can potentially do a better job than more conventional methods, so long as they're provided with enough content.
Another aspect of context that could be relevant to your work may be how people are nested within households. In some record linkage scenarios you can run a linkage on household membership and use this to make person linkages more precise. I imagine an LLM agent could also use this information effectively if it were explicitly provided, but sometimes they miss logical leaps like this
> Half the point of this project is showing off some amazing public-domain natural-history illustrations. Over 800 cut-outs covering more than 400 species, every one taken from a real plate and hand-curated for this project (no art is AI-generated, though some has been retouched with AI).
I've been experimenting for a year or two making games that make mental arithmetic practice fun for kids. The latest is
https://rupertlinacre.com/keep_it_going/ an infinite rollercoaster, which I think is one of the more successful attempts. There are various others on the homepage. My son also really likes arithmetic annihilation and maths vs monsters.
Interesting. I'm surprised they haven't prioritised/deliberately trained for this more because of how useful it is to ask codex to generate some images/assets/sprites when building sill games. It would dramatically enhance how polished it's games were.
That said for single images the old model was already okayish for prototypes
This is a quick prototype, made for my 7yo who loves buses.
A few tips:
- Click the freeze icon to be able to zoom and pan without it changing the location of the lens
- Double click to position the lens
Thanks for feedback about the data. The bus stop and route data comes from the Department for Transport’s Bus Open Data Service (BODS), using the national GTFS feed. It seems some things like Manchester metro creep in.
All these caveats aside, as soon as I got this working it felt like a promising direction. I will pay attention to everyone's comments and suggestions and iterate! Thank you!
Incidentally there's a bunch of other free stuff I built for my 7yo on the root domain
It'd be nice to be able to permalink to the view for a specific location
While that'd be useful for things like telling someone else what buses they can get, planning a trip, etc, what I actually tried to do was to link to the Killermont Street bus station in Glasgow; Aztec Camera had a sentimental song about late night departures from there - leaving your friends and heading south to look for work - that runs:
As the ships and the steel
Slip away to the cry of "Compete"
There's a message for us
We can get there by bus
From Killermont Street
And indeed you can...buses all over the place. But I can't link to it :)
it's showing a lot of rail/etc. replacement bus routes, which I wouldn't consider typical as they (hopefully) only run very rarely - such as the "DLR" replacement bus route, and "RB1" replacement bus route for the thames clipper in london
Thanks for this! Really fascinating to see how coverage differs.
I expected the UX to work more like:
- Freeze is on by default (or there is no concept of 'freeze'). I can just move around without my screen turning to a lightning strike of random routes.
It does not know enough about the records in the context of the overall dataset:
- what is the data quality and to what extent do we expect a errors in some fields - how unusual are certain values such as names in the context of the dataset as a whole, e.g. some names would be very common in some countries but rare in others.
I've written in more detail about this here: https://www.robinlinacre.com/fellegi_sunter_accuracy/
reply