Lead developer of Splink. Data scientist at Ministry of Justice. Trustee, GiveDirectly UK. Pledgee, https://xitter.cf/t.co/GRyQA85s7n. All views my own.

United Kingdom
Joined January 2013
Pleased to announce the release of Splink version 4.0.0 today. It's now: 👩‍🔬 Easier to use 🚀 Faster ⚡ More scalable 🛠️ Easier to improve For the uninitiated, Splink is a free library for record linkage and deduplication at scale See 🧵 for links and more 1/3
3
5
1
21
6,551
We're very pleased to release Splink 5, which is now more scalable, faster to train models and lighter to install
🤖 Made with AI
2
2
5
153
You can find more details about the release here: moj-analytical-services.gith…
24
In case you missed it. This has since been featured in the Data Elixir, Data Science Weekly and Quantum of Sollazzo newsletters
New blog: Data Science in the Age of AI robinlinacre.com/data_scienc… LLMs are the biggest shakeup to the profession I've ever experienced. The post uses examples to look at how the job has changed and how to use agents effectively.
3
219
A sneak peak at Splink 5 beta performance: just ran a 1bn input row/10bn comparison dedupe on synthetic data, on 192vCPU EC2 instance, using @duckdb 2.0 prerelease. Runtime: 8.5 mins, cost <$1.00 on a spot instance. This is at least 10x faster than previous versions
3
3
12
330
Splink 5 pre-releases available on PyPI, latest code on GitHub github.com/moj-analytical-se…
1
1
68
Just checked old messages. Splink v1 (which was very fast and scalable at the time) had following stats: 16m input, creating 100m comparisons: took 57 minutes at a cost of £3.50 in PySpark on AWS Glue. So 6 years work = >600x speedup, and it's now 350x cheaper!
2
31
New blog: Data Science in the Age of AI robinlinacre.com/data_scienc… LLMs are the biggest shakeup to the profession I've ever experienced. The post uses examples to look at how the job has changed and how to use agents effectively.
1
1
6
466
Robin Linacre retweeted
Today, @ducklabs_com is joining @awscloud. The move is expected to be completed by early September. Joining AWS gives DuckLabs the resources and reach to bring DuckDB, DuckLake, and the Quack protocol to many more developers and organizations – and to pursue ideas at a scale that would have been difficult for us to reach alone. The DuckLabs team will remain together in Amsterdam and will continue working for the Duck Stack community as an AWS subsidiary. Most importantly, #DuckDB and the other open source components of the Duck Stack will remain free and open source under the MIT license, with the non-profit DuckDB Foundation continuing its stewardship of the projects. This is a significant moment for DuckLabs and the Duck Stack community. It marks the end of one chapter that we are immensely proud of, and the beginning of another that we believe will take DuckDB much further. Read the full announcement here: ducklabs.com/ducklabs-is-joi… #AWS
69
351
168
1,600
275,548
My son loves buses! I made an app called buslens that shows you all the places you can get to by bus from near your current location, or any other location:
1
2
130
Turns out it's popular! third place on Hacker News!
16
Robin Linacre retweeted
Quack, quack! A DuckDB v2.0 preview is here! 🦆 🦆⚡ In this post, #DuckDB co-creators Mark Raasveldt and Hannes Mühleisen preview the headline features of DuckDB v2.0 (expected to arrive this autumn): • DuckDB as a server • Triggers • The VARIANT type • Asynchronous I/O • A new SQL parser • A new storage format • and much more! 🤩 Dive into the details: duckdb.org/2026/08/17/duckdb…
8
121
13
566
82,935
You can now automatically turn your Splink model settings.json into a live in-browser linkage model. Simply drag in your .json and get an interactive webapp robinlinacre.com/splink_sett…
1
1
146
Features: - Live edit test records and see the match score - Waterfall visualisation - Visualise match weights and m and u proabilities - See which comparison levels are activated, and their associated scores - See which blocking rules are activated by the records
1
39
Uses DuckDB wasm, and so only supports models trained using the DuckDB backend. This is an experiment - let me know any feedback!
44