Robin Linacre

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

Amazing that in a few hours, it possible to build one of the best versions of this on the web. I'm somewhat optimistic that we'll see more things like this, and for people who care they'll be easier to find, so we won't have to put up with ads/monetisation/spam in edu tools.

The country quiz now has: - Capital cities mode - Single continent mode - 'What country is highlighted' mode - More detailed borders - 4k mode, with much bigger map - Choice of map projection Access via options menu. rupertlinacre.com/country_quiz/

uk_address_matcher v1.0.1 is released: - Hugely reduced memory usage, especially when matching to full UK. - Over 30% faster - Now supports duckdb 1.4.4 and 1.5.0 - New docs on choosing a matching threshold and optimising accuracy here: moj-analytical-services.github.io/uk_address_mat…

Another one for English monarchs: rupertlinacre.com/english_monarc…

I have been enjoying playing Sporcle's countries of the world quiz with my son, so I made a fancier version. Play here: rupertlinacre.com/country_quiz/

We're particularly proud of how easy this is to use. The following 2 minute video demos the end-to-end process of matching 100k council tax records. This process is more fully documented here: moj-analytical-services.github.io/uk_address_mat…

Docs: moj-analytical-services.github.io/uk_address_mat… Code: github.com/moj-analytical… Discussion forum: github.com/moj-analytical…

We are pleased to release `uk_address_matcher`, a free Python package for address matching and geocoding, developed by Tom Hepworth and me. The package has several aims: simplicity, speed and accuracy.

@karpathy @airesearch12 That it's spec driven development rather than idea driven development highlights a crucial limitation of the models. Figuring out what the spec should be is often the hard problem; at least it's much quicker to iterate towards it now.

@airesearch12 💯 @ Spec-driven development It's the limit of imperative -> declarative transition, basically being declarative entirely. Relatedly my mind was recently blown by dbreunig.com/2026/01/08/a-s… , extreme and early but inspiring example.

A few random notes from claude coding quite a bit last few weeks. Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent. IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They will implement an inefficient, bloated, brittle construction over 1000 lines of code and it's up to you to be like "umm couldn't you just do this instead?" and they will be like "of course!" and immediately cut it down to 100 lines. They still sometimes change/remove comments and code they don't like or don't sufficiently understand as side effects, even if it is orthogonal to the task at hand. All of this happens despite a few simple attempts to fix it via instructions in CLAUDE . md. Despite all these issues, it is still a net huge improvement and it's very difficult to imagine going back to manual coding. TLDR everyone has their developing flow, my current is a small few CC sessions on the left in ghostty windows/tabs and an IDE on the right for viewing the code + manual edits. Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. You realize that stamina is a core bottleneck to work and that with LLMs in hand it has been dramatically increased. Speedups. It's not clear how to measure the "speedup" of LLM assistance. Certainly I feel net way faster at what I was going to do, but the main effect is that I do a lot more than I was going to do because 1) I can code up all kinds of things that just wouldn't have been worth coding before and 2) I can approach code that I couldn't work on before because of knowledge/skill issue. So certainly it's speedup, but it's possibly a lot more an expansion. Leverage. LLMs are exceptionally good at looping until they meet specific goals and this is where most of the "feel the AGI" magic is to be found. Don't tell it what to do, give it success criteria and watch it go. Get it to write tests first and then pass them. Put it in the loop with a browser MCP. Write the naive algorithm that is very likely correct first, then ask it to optimize it while preserving correctness. Change your approach from imperative to declarative to get the agents looping longer and gain leverage. Fun. I didn't anticipate that with agents programming feels *more* fun because a lot of the fill in the blanks drudgery is removed and what remains is the creative part. I also feel less blocked/stuck (which is not fun) and I experience a lot more courage because there's almost always a way to work hand in hand with it to make some positive progress. I have seen the opposite sentiment from other people too; LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building. Atrophy. I've already noticed that I am slowly starting to atrophy my ability to write code manually. Generation (writing code) and discrimination (reading code) are different capabilities in the brain. Largely due to all the little mostly syntactic details involved in programming, you can review code just fine even if you struggle to write it. Slopacolypse. I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media. We're also going to see a lot more AI hype productivity theater (is that even possible?), on the side of actual, real improvements. Questions. A few of the questions on my mind: - What happens to the "10X engineer" - the ratio of productivity between the mean and the max engineer? It's quite possible that this grows *a lot*. - Armed with LLMs, do generalists increasingly outperform specialists? LLMs are a lot better at fill in the blanks (the micro) than grand strategy (the macro). - What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music? - How much of society is bottlenecked by digital knowledge work? TLDR Where does this leave us? LLM agent capabilities (Claude & Codex especially) have crossed some kind of threshold of coherence around December 2025 and caused a phase shift in software engineering and closely related. The intelligence part suddenly feels quite a bit ahead of all the rest of it - integrations (tools, knowledge), the necessity for new organizational workflows, processes, diffusion more generally. 2026 is going to be a high energy year as the industry metabolizes the new capability.

In case you missed it: New blog: Respectful use of AI in software development teams. 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? Link inside

@thomasforth @TheDataCity Thanks!, appreciate the kind words. For those interested in record linkage I'm the lead author of Splink. I tweet mostly about record linkage and open source in gvt

An example of UK government being great. Ministry of Justice needed to do messy data linking more quickly and reliably than existing methods. Developed the system. Released it. Now it's used all over the place, including by us at @TheDataCity. It's great! github.com/moj-analytical…

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

@rough__sea I largely agree. For me, the distinction is SWEs need to _understand_ the system , not write every line of code. If a critical system goes down, its their responsibility to understand it well enough to fix it in a principled and correct way.

This has been said a thousand times before, but allow me to add my own voice: the era of humans writing code is over. Disturbing for those of us who identify as SWEs, but no less true. That's not to say SWEs don't have work to do, but writing syntax directly is not it.

@simonw would love to hear your thoughts - do you think this is too conservative?

New blog: Respectful use of AI in software development teams robinlinacre.com/respectful_use… 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?