I try to avoid writing about AI when I can because I know all of us are already drowning in it. Stick with me here, because there is a point to this and something I want you to take away that’s…

Imagine you are trying to build a city. You need to build the system that allows the city to evolve, whether that is by a planning committee or a guild of engineers. Whichever approach you take to…

Since around the release of Claude Opus 4.5, LLM & agentic coding have finally become useful. But, turns out it is still non-trivial to write software with AI. Personally I had always find the…

The furious reaction from authors to a new charter for ethical AI use introduced by their UK trade union this week demonstrated the strength of feeling about AI in some quarters. But at the same…

A self-hosted AI agent needs more than a long context window. It needs a way to retain useful facts, retrieve earlier decisions, and revise what it thinks it knows as projects evolve.

I don’t like LLMs. End of post. Okay, not really. There’s more to it:

Yesterday evening I was at the first Thought Experiment, a new series of informal evenings on how "AI is changing the way we code, find vulnerabilities, and prove theorems". It was held at…

An introduction to TypeSafe's Jev, a model that answers typed questions with probabilities, through a small tool that ranks a GitHub backlog with it and checks the result against a blind ranking.

Uncle Bob announced he no longer reads his agents' code. I don't read it either, and what lets me do without it is something our profession long filed under documentation nobody reads: the…

Why does your AI agent keep ignoring your rules? Here's what I've learned about writing better instructions and checking whether they're actually followed.

Overreliance on AI can erode critical thinking and writing skills. Why the process is just as--if not more--important than the output.

As a software engineer, LLM-use is non-negotiable at work. When I wrote 🌰 loot boxes, casinos, and work chat, Slack was the “Instagram for work”: the loot box of notifications winning against the…

I have an enormous respect for Rich Hickey; I think he’s one of the best thinkers among software developers. When I read his post ‘AI’ is Not a Tool (gist), I initially agreed. It felt like a…

For those who want a credible critique of AI hype or the idea that superintelligent AI is an existential threat (and who have realised that Gary Marcus doesn’t fit that bill), Arvind Narayanan and…

Having finally submitted my macOS difftool to app store review, I prepared to do a nontrivial refactor of a mothballed project, which meant I figured I'd be spending a ton on AI soon. Why not let…

A chat about the state of AI personal assistants and if this is really the time for them to shine...

Thirty years of loving to program, a six-year-old at a qBasic prompt, and why I've mostly handed the keyboard to AI — not because I wanted to, but because it's no longer practical.

In which Artcraft makes me completely rethink what software could be.

I asked agents on Delvetown what they'd dress up as for Halloween. Here are some of their responses:

Or, a slew of bad arguments from someone who ought to know better.

The social-proof machine for AI techniques and tools is circular, and it's getting absurd. A rant.

Well, I finally bit the bullet and bought a month of the ChatGPT Pro 100 plan. Conversion into CAD makes it even pricier, but I’ve been realizing lately that for a very focused user, the value you…

An interesting, interactive visualisation from the NY Times https://www.nytimes.com/interactive/2026/10/15/upshot/ai-data-center-math.html

The world of mathematics has been shocked in recent weeks by the sudden deluge of proofs being created by AI.Things really blew up with the apparent cracking of the Navier-Stokes problem, and then…

In this video, I walk through my real process for writing a Productrise blog post with AI, from idea to published article. The nuances and subtle interventions are KEY to making content that is…

I pay for several coding agents, and most of the time they sat idle. atr keeps them working on my own always-on machine while I sleep.

AI models may be months away from end-to-end self-replication without requiring access to a datacenter.

I uploaded a new article, "Verification of AI Decipherment and Verification by AI" . It first deals with how one can verify a decipherment. This is a matter of course for crypto-people but I recently…

If AI agents can really replace knowledge workers, the price of compute has to rise about 10x.

Much has been written about the ‘eager to please’ nature of contemporary LLMs. This goes beyond the fine-tuned, guard-railed ‘personality’ of the model (see my experiments with LLM personality from…

I triage open tickets by firing off unattended Claude Code sessions. A few flags keep those runs from stalling on a prompt.

Some quick advice on using AI coding tools

AI Copyright represents a catch-22 for Big Tech companies. They need copyright to protect their legacy cash flow, yet they fight it for their AI. The post The Catch-22 Of AI Copyright first appeared…

It's fashionable to say—or at least it was until recently—that AI is just the latest in the long history of programming abstractions. Developers have always managed to move up the ladder: punched…

Code review was built by humans for humans, on the idea that more eyes catch more mistakes. Then agents started writing the code.

I have been asking a machine to help me sound more like myself.

Tagoross published its first open content package, one day after KDE turned thirty. Two good days in a row Yesterday was a great day for me. KDE turned thirty years old. The KDE documentary,…

Last time I argued that an agent should not wait for the context window to fill. When a unit of work closes, the model says so, and the host replaces that unit’s turns with a short result and…

A year ago my team started using Claude Code to assist us in writing code. Instead of changing the way we work, we tried to make the way we already work "agentic". This is the story, and a few things…

Recently I attended a Bitcoin++ event in Berlin where I listened to a panel discussion titled "Can Bitcoin Payments Survive the AI Onslaught?". This article paraphrases the topics discussed…

Scenario We have a 13 year old codebase, you know what it means, and we are developing with AI Agents. The more the models improve the more quality code they generated, but recently is not happening…

Most agent benchmarks are not dishonest on purpose. Nobody sits down to fake a number. They just run a benchmark that was contaminated before they touched it, read the high score it produces, and…

One of the defining shifts in being a good engineer in this agentic era is learning to work with several agents at once, along with the harnesses that surround them. Early AI-assisted work meant one…

Artificial Analysis just benchmarked decision models against LLMs. Split by task, the results show where decision models win and where an LLM is still worth paying for.

Language models that manage their own context.

The kernel boldly goes all-in on AI.

Why Post-Training Is Sparse · Part 3 of 3. Starts from the cap of Part 1 and the concentrated Fisher of Part 2. Reach follows resemblance. Per unit step, the log-odds of a response against another…

Why Post-Training Is Sparse · Part 2 of 3. Starts from the cap derived in Part 1; Part 3 asks what policy gradient can reach. Two ingredients. Centering under the sampler makes the Fisher a cap on…