Robin Linacre
@robinlinacre.bsky.social
Lead developer of Splink. Data scientist at Ministry of Justice. Trustee, GiveDirectly UK. Pledgee, http://givingwhatwecan.org. All views my own.
In case you missed it: New blog: Respectful use of AI in software development teams
www.robinlinacre.com/respectful_u...
LLMs are increasingly able to write production quality code. But what cognitive work can be delegated to LLMs without damaging the health of the team?
www.robinlinacre.com/respectful_u...
LLMs are increasingly able to write production quality code. But what cognitive work can be delegated to LLMs without damaging the health of the team?
robinlinacre.com
January 23, 2026 at 6:57 PM
In case you missed it: New blog: Respectful use of AI in software development teams
www.robinlinacre.com/respectful_u...
LLMs are increasingly able to write production quality code. But what cognitive work can be delegated to LLMs without damaging the health of the team?
www.robinlinacre.com/respectful_u...
LLMs are increasingly able to write production quality code. But what cognitive work can be delegated to LLMs without damaging the health of the team?
For anyone with FOMO wondering whether to pay for Opus 4.5/Claude Code, my experience is that OpenAI Codex is very similar in performance. i.e. both are excellent, but Claude Code is not a magic unlock
January 20, 2026 at 6:10 PM
For anyone with FOMO wondering whether to pay for Opus 4.5/Claude Code, my experience is that OpenAI Codex is very similar in performance. i.e. both are excellent, but Claude Code is not a magic unlock
Reposted by Robin Linacre
Excited to be a part of the initiative to "Move Fast and Fix Things", announced in Chief Secretary to the Prime Minister's speech today. One measure is an expansion of the No10 Innovation Fellowship, for which we've launched a new website!
fellows.ai.gov.uk
Speech: www.gov.uk/government/s...
fellows.ai.gov.uk
Speech: www.gov.uk/government/s...
January 20, 2026 at 3:46 PM
Excited to be a part of the initiative to "Move Fast and Fix Things", announced in Chief Secretary to the Prime Minister's speech today. One measure is an expansion of the No10 Innovation Fellowship, for which we've launched a new website!
fellows.ai.gov.uk
Speech: www.gov.uk/government/s...
fellows.ai.gov.uk
Speech: www.gov.uk/government/s...
New blog: Respectful use of AI in software development teams
robinlinacre.com/respectful_u...
LLMs are increasingly able to write production quality code. But what cognitive work can be delegated to LLMs without damaging the health of the team?
robinlinacre.com/respectful_u...
LLMs are increasingly able to write production quality code. But what cognitive work can be delegated to LLMs without damaging the health of the team?
January 12, 2026 at 8:42 AM
New blog: Respectful use of AI in software development teams
robinlinacre.com/respectful_u...
LLMs are increasingly able to write production quality code. But what cognitive work can be delegated to LLMs without damaging the health of the team?
robinlinacre.com/respectful_u...
LLMs are increasingly able to write production quality code. But what cognitive work can be delegated to LLMs without damaging the health of the team?
Made a simple game to help my daughter learn her alphabet. Took about 1 day for full code, >200 images >200 voice files and music
nano-banana-pro is incredible. But it's also so quick to vibe code image and audio processing scripts.
robinlinacre.com/bee_letters/
github.com/RobinL/bee_l...
nano-banana-pro is incredible. But it's also so quick to vibe code image and audio processing scripts.
robinlinacre.com/bee_letters/
github.com/RobinL/bee_l...
December 6, 2025 at 5:13 PM
Made a simple game to help my daughter learn her alphabet. Took about 1 day for full code, >200 images >200 voice files and music
nano-banana-pro is incredible. But it's also so quick to vibe code image and audio processing scripts.
robinlinacre.com/bee_letters/
github.com/RobinL/bee_l...
nano-banana-pro is incredible. But it's also so quick to vibe code image and audio processing scripts.
robinlinacre.com/bee_letters/
github.com/RobinL/bee_l...
I struggle to find no-nonsense, free and 'fun'(ish) maths games for my son (7yo) so I have been making a few
Here's another one: Maths vs monsters. This is his fav so far
rupertlinacre.com/maths_vs_mon...
Code:
github.com/rupertLinacr...
Other games/maths utilities:
rupertlinacre.com
Here's another one: Maths vs monsters. This is his fav so far
rupertlinacre.com/maths_vs_mon...
Code:
github.com/rupertLinacr...
Other games/maths utilities:
rupertlinacre.com
November 30, 2025 at 5:02 PM
I struggle to find no-nonsense, free and 'fun'(ish) maths games for my son (7yo) so I have been making a few
Here's another one: Maths vs monsters. This is his fav so far
rupertlinacre.com/maths_vs_mon...
Code:
github.com/rupertLinacr...
Other games/maths utilities:
rupertlinacre.com
Here's another one: Maths vs monsters. This is his fav so far
rupertlinacre.com/maths_vs_mon...
Code:
github.com/rupertLinacr...
Other games/maths utilities:
rupertlinacre.com
Reposted by Robin Linacre
OpenUK Awards 25 Open Data Category sponsored by Open Data Institute, Shortlist is live, congratulations to the shortlisted nominees: Ministry of Justice UK Splink Team (@robinlinacre.bsky.social), OpenActive, and UK Power Networks (Yiu-Shing Pang) 🍾🥂🏆
#openukawards #opensource #opendata
#openukawards #opensource #opendata
November 4, 2025 at 11:30 AM
OpenUK Awards 25 Open Data Category sponsored by Open Data Institute, Shortlist is live, congratulations to the shortlisted nominees: Ministry of Justice UK Splink Team (@robinlinacre.bsky.social), OpenActive, and UK Power Networks (Yiu-Shing Pang) 🍾🥂🏆
#openukawards #opensource #opendata
#openukawards #opensource #opendata
Reposted by Robin Linacre
More progress on #openaddresses:
Islington Council in London has released its Council Tax address list for re-use as #opendata under the Open Government Licence www.owenboswarva.com/blog/post-ad...
I've made a geocoded version by adding coordinates from ONS
#FOI #localgov #UKhousing #proptech
Islington Council in London has released its Council Tax address list for re-use as #opendata under the Open Government Licence www.owenboswarva.com/blog/post-ad...
I've made a geocoded version by adding coordinates from ONS
#FOI #localgov #UKhousing #proptech
October 28, 2025 at 8:46 AM
More progress on #openaddresses:
Islington Council in London has released its Council Tax address list for re-use as #opendata under the Open Government Licence www.owenboswarva.com/blog/post-ad...
I've made a geocoded version by adding coordinates from ONS
#FOI #localgov #UKhousing #proptech
Islington Council in London has released its Council Tax address list for re-use as #opendata under the Open Government Licence www.owenboswarva.com/blog/post-ad...
I've made a geocoded version by adding coordinates from ONS
#FOI #localgov #UKhousing #proptech
New ✨interactive✨ explainer: Address matching using a fault tolerant trie:
robinlinacre.com/fault_tolera...
Which illustrates a powerful technique for address matching that we're currently working on building into uk_address_matcher (github.com/moj-analytic...)
robinlinacre.com/fault_tolera...
Which illustrates a powerful technique for address matching that we're currently working on building into uk_address_matcher (github.com/moj-analytic...)
September 24, 2025 at 7:51 AM
New ✨interactive✨ explainer: Address matching using a fault tolerant trie:
robinlinacre.com/fault_tolera...
Which illustrates a powerful technique for address matching that we're currently working on building into uk_address_matcher (github.com/moj-analytic...)
robinlinacre.com/fault_tolera...
Which illustrates a powerful technique for address matching that we're currently working on building into uk_address_matcher (github.com/moj-analytic...)
When working a complex postgres schema, I find it time consuming to figure out the joins.
I had an idea: a 'join generator' that traverses the relationship graph for you, and writes the joins.
You give it a dump of the postgres schema, and it gives you a UI.
www.robinlinacre.com/vite_live_pg...
I had an idea: a 'join generator' that traverses the relationship graph for you, and writes the joins.
You give it a dump of the postgres schema, and it gives you a UI.
www.robinlinacre.com/vite_live_pg...
August 18, 2025 at 6:40 AM
When working a complex postgres schema, I find it time consuming to figure out the joins.
I had an idea: a 'join generator' that traverses the relationship graph for you, and writes the joins.
You give it a dump of the postgres schema, and it gives you a UI.
www.robinlinacre.com/vite_live_pg...
I had an idea: a 'join generator' that traverses the relationship graph for you, and writes the joins.
You give it a dump of the postgres schema, and it gives you a UI.
www.robinlinacre.com/vite_live_pg...
We're working on a DuckDB community extension called `splink_udfs` to add some record linkage related functions to DuckDB. It's currently very much WIP, but you can already use it wherever you're using DuckDB.
github.com/moj-analytic...
github.com/moj-analytic...
July 22, 2025 at 4:50 PM
We're working on a DuckDB community extension called `splink_udfs` to add some record linkage related functions to DuckDB. It's currently very much WIP, but you can already use it wherever you're using DuckDB.
github.com/moj-analytic...
github.com/moj-analytic...
If you're using Splink with DuckDB you should see significant speed improvements by updating to DuckDB 1.3.x. You can also add more granularity to your comparison levels statements without an impact on run times. Depending on your model spec, it could be twice as fast or better.
Speed enhancement: 'Pushing up' common elements of CASE statements into reused computations by RobinL · Pull Request #2738 · moj-analytical-services/splink
This is a clean rewrite of #2630. The rationale is explained further in #2580, but in a nutshell it eliminates repeated computations of potentially expensive functions in some backends, e.g
CASE
...
github.com
July 15, 2025 at 4:46 PM
If you're using Splink with DuckDB you should see significant speed improvements by updating to DuckDB 1.3.x. You can also add more granularity to your comparison levels statements without an impact on run times. Depending on your model spec, it could be twice as fast or better.
My most commonly used pattern for AI coding: Dump entire source code into Gemini 2.5 pro, write prompt specifying what I want, and then: Give precise instructions for an LLM to follow to implement this feature. Break the solution down into steps where each step is verifiable.
July 11, 2025 at 8:33 AM
My most commonly used pattern for AI coding: Dump entire source code into Gemini 2.5 pro, write prompt specifying what I want, and then: Give precise instructions for an LLM to follow to implement this feature. Break the solution down into steps where each step is verifiable.
I have been working on a free, high performance address matcher. I've written up some key tricks, techniques, and ideas into a blog post here: www.robinlinacre.com/address_matc...
Building Accurate Address Matching Systems
A bag of tricks to improve the accuracy of geocoding
www.robinlinacre.com
July 5, 2025 at 10:00 AM
I have been working on a free, high performance address matcher. I've written up some key tricks, techniques, and ideas into a blog post here: www.robinlinacre.com/address_matc...
The 'build' button in google AI studio is unbelievably good. I had an idea to visualise fractions, three prompts total and it's pretty close to something useful (it does this for any arbitrary fractions). Even the one-shot attempt was pretty good
May 22, 2025 at 8:15 PM
The 'build' button in google AI studio is unbelievably good. I had an idea to visualise fractions, three prompts total and it's pretty close to something useful (it does this for any arbitrary fractions). Even the one-shot attempt was pretty good
My PyData Global talk "Rapid deduplication and fuzzy matching of large datasets using Splink" is now on Youtube: www.youtube.com/watch?v=eQtF...
Robin Linacre - Rapid deduplication and fuzzy matching of large datasets using Splink
YouTube video by PyData
www.youtube.com
April 17, 2025 at 3:03 PM
My PyData Global talk "Rapid deduplication and fuzzy matching of large datasets using Splink" is now on Youtube: www.youtube.com/watch?v=eQtF...
I see too much focus on trying to find applications of LLMs to help other people 'at scale' with their jobs. At the moment, the output of LLMs is rarely useful for business rules or passive consumption. The lower hanging fruit is helping people use AI directly & however they see fit in their job.
April 4, 2025 at 8:38 AM
I see too much focus on trying to find applications of LLMs to help other people 'at scale' with their jobs. At the moment, the output of LLMs is rarely useful for business rules or passive consumption. The lower hanging fruit is helping people use AI directly & however they see fit in their job.
If you're using duckdb in a python script or jupyter notebook, you can run con.execute('CALL start_ui()') at any point, and the ui will pop right up in your web browser with the current database automatically available.
(I knew about the UI, but I had missed this trick!)
(I knew about the UI, but I had missed this trick!)
April 1, 2025 at 6:28 AM
If you're using duckdb in a python script or jupyter notebook, you can run con.execute('CALL start_ui()') at any point, and the ui will pop right up in your web browser with the current database automatically available.
(I knew about the UI, but I had missed this trick!)
(I knew about the UI, but I had missed this trick!)
Gemini 2.5 pro is really good. Grok 3 felt like a big step forwards and was my 'go-to' for hard problems, and this feels like another significant step forward.
So nice with small codebases to be able put everything into context (I use github.com/simonw/files... )
So nice with small codebases to be able put everything into context (I use github.com/simonw/files... )
GitHub - simonw/files-to-prompt: Concatenate a directory full of files into a single prompt for use with LLMs
Concatenate a directory full of files into a single prompt for use with LLMs - simonw/files-to-prompt
github.com
March 29, 2025 at 11:39 AM
Gemini 2.5 pro is really good. Grok 3 felt like a big step forwards and was my 'go-to' for hard problems, and this feels like another significant step forward.
So nice with small codebases to be able put everything into context (I use github.com/simonw/files... )
So nice with small codebases to be able put everything into context (I use github.com/simonw/files... )
Reposted by Robin Linacre
Ended up writing a follow up post with the final approach and learnings from getting this running on GitHub Actions!
All original datasets weight more than 500GB combined. The final ones published on 🤗, only 1 GB. Took some tinkering to get there but was fun!
davidgasquez.com/exporting-in...
All original datasets weight more than 500GB combined. The final ones published on 🤗, only 1 GB. Took some tinkering to get there but was fun!
davidgasquez.com/exporting-in...
March 20, 2025 at 12:56 PM
Ended up writing a follow up post with the final approach and learnings from getting this running on GitHub Actions!
All original datasets weight more than 500GB combined. The final ones published on 🤗, only 1 GB. Took some tinkering to get there but was fun!
davidgasquez.com/exporting-in...
All original datasets weight more than 500GB combined. The final ones published on 🤗, only 1 GB. Took some tinkering to get there but was fun!
davidgasquez.com/exporting-in...
New blog: Why DuckDB is my first choice for data processing:
www.robinlinacre.com/recommend_du...
www.robinlinacre.com/recommend_du...
Why DuckDB is my first choice for data processing
Why DuckDB has become my go-to tool for data processing, offering simplicity, speed, and powerful features.
www.robinlinacre.com
March 16, 2025 at 7:17 PM
New blog: Why DuckDB is my first choice for data processing:
www.robinlinacre.com/recommend_du...
www.robinlinacre.com/recommend_du...
I vibe coded a primary school maths breakout game - aimed to be fun and educational.
rupertlinacre.com/breakout_mat...
In the process I created and open sourced a maths problem generator aligned to the national curriculum, so you can vibe code your own maths games!
www.npmjs.com/package/math...
rupertlinacre.com/breakout_mat...
In the process I created and open sourced a maths problem generator aligned to the national curriculum, so you can vibe code your own maths games!
www.npmjs.com/package/math...
Breakout Maths Game
rupertlinacre.com
March 15, 2025 at 7:40 PM
I vibe coded a primary school maths breakout game - aimed to be fun and educational.
rupertlinacre.com/breakout_mat...
In the process I created and open sourced a maths problem generator aligned to the national curriculum, so you can vibe code your own maths games!
www.npmjs.com/package/math...
rupertlinacre.com/breakout_mat...
In the process I created and open sourced a maths problem generator aligned to the national curriculum, so you can vibe code your own maths games!
www.npmjs.com/package/math...
Just added an example/tutorial to the Splink docs of matching business data.
It uses some feature engineering tricks that help improve accuracy vs. just fuzzy matching on names.
moj-analytical-services.github.io/splink/demos...
It uses some feature engineering tricks that help improve accuracy vs. just fuzzy matching on names.
moj-analytical-services.github.io/splink/demos...
Linking businesses - Splink
moj-analytical-services.github.io
February 14, 2025 at 2:01 PM
Just added an example/tutorial to the Splink docs of matching business data.
It uses some feature engineering tricks that help improve accuracy vs. just fuzzy matching on names.
moj-analytical-services.github.io/splink/demos...
It uses some feature engineering tricks that help improve accuracy vs. just fuzzy matching on names.
moj-analytical-services.github.io/splink/demos...
I think the single most productivity-enhancing use of LLMs in gov would be give all devs and data scientists access to Cursor (or equivalent). I am not yet convinced of the widespread value of 'behind the scenes' uses of LLMs, but v. bullish on skilled human-in-the-loop uses, especially coding
February 13, 2025 at 1:16 PM
I think the single most productivity-enhancing use of LLMs in gov would be give all devs and data scientists access to Cursor (or equivalent). I am not yet convinced of the widespread value of 'behind the scenes' uses of LLMs, but v. bullish on skilled human-in-the-loop uses, especially coding