The online whiteboard of Kristofer Palmvik
Paperclip is a Node.js server and React UI that orchestrates a team of AI agents to run a business. Bring your own agents, assign goals, and track your agents' work and costs from one dashboard. It looks like a task manager — but under the hood it has org charts, budgets, governance, goal alignment, and agent coordination.
To design the most effective combinations, the engineers used AI to evolve novel body configurations. Instead of sticking with standard dog- or human-like designs, the AI churned out strange new “species” of machines that no human engineer would have conceived. When connected to other modules, the metamachines undulate like seals, bound like lizards, or spring like kangaroos.
Operators of AI models in Europe should pay "a revenue-based levy... reflecting their use of content publicly available online," Arthur Mensch wrote in an op-ed for the Financial Times. "Proceeds would flow into a central European fund dedicated to investing in new content creation and supporting Europe's cultural sectors," he added.
The act of programming has lived in extract for 45 years and we’re used to that,” he said. Then the genie of generative AI coding assistants escaped from the bottle, “and all of those certainties have been thrown out of the window,” he said. Exploration doesn’t look very much like engineering from the books. “It’s about cutting corners to get answers, throwing away what you’ve done, starting over, being creative, sniffing out opportunities,” Beck said.
Self-hosted GitHub Actions runners can be weaponized into persistent backdoors that communicate entirely over trusted channels. Because all traffic flows to github.com, traditional network defenses are largely blind to the threat.
Everyone is talking about how quickly they’re building things, how many agents they’re using at the same time, and how much time they’re saving. I feel like if I’m working at a regular speed, I’m not doing enough.
A garden is a collection of evolving ideas that aren’t strictly organised by their publication date. They’re inherently exploratory – notes are linked through contextual associations. They aren’t refined or complete - notes are published as half-finished thoughts that will grow and evolve over time. They’re less rigid, less performative, and less perfect than the personal websites we’re used to seeing.
In my opinion and in short : I think digital gardens as digital spaces where people grows their ideas from seed to tree : 🌱 -> ☘️ -> 🍀 -> 🌿 -> 🌲 -> 🎄
Semantic anchors are well-defined terms, methodologies, and frameworks that serve as reference points when communicating with Large Language Models (LLMs). They act as shared vocabulary that triggers specific, contextually rich knowledge domains within an LLM’s training data. Think of them as shortcuts to rich context - instead of explaining a complex methodology from scratch, you can invoke a semantic anchor and the LLM will activate its entire knowledge base about that concept.
The developers who will be best positioned in three years are the ones who started genuinely engaging with agentic coding today. Not using it as a fancy autocomplete. Actually engaging with it, letting go of implementation as the primary measure of their contribution, developing fluency in a new kind of collaboration between human judgment and machine capability.
Our migration to Hive Gateway is a story of pragmatic engineering execution. A small team replaced the core routing layer of Sweden’s largest property platform in under two months, with zero user-visible downtime and no latency regression.
Throughout the ages, humans have come up with ideas. Some ideas never become more than a thought. Others spread globally, affecting people for a long time. The life of ideas seems to be an eternal cycle of birth, life, death, and rebirth.
They may look at a very high-fidelity, live-data prototype and think that it can’t be all that hard to make the leap to something we can actually sell and service and that our customers can run their business on. But I’ve now witnessed more than a few product managers embarrass themselves in front of their engineers. So this article is intended for these people.
the whenwords library contains no code. Instead, whenwords contains specs and tests. The installation instructions are comically simple, just a prompt to paste into Claude, Codex, Cursor, whatever.
Temporal is not just a better API. It's proof that the JavaScript community can solve long-standing problems together. After nearly 30 years, JavaScript finally has a modern datetime API. And this time, we got it right.
As AI generates more of the code, the nature of how teams collaborate around changes is shifting. Review is one of the few systematic places where humans on a team exercise judgment together about the system they share. What they’re judging is changing – less mechanical correctness, more intent and direction – but the collaborative act is worth protecting.
AI in the workplace is transforming the technical systems. Much less attention is being paid to the cultural systems that surround it. New tools can be exciting, especially to management and motivated individual contributors. For the rest of your teams they can clearly be seen as threats to the “way we do things around here.” If we don’t address those systemic cultural issues we’ll never be able to take full advantage of these new tools in a way that truly maximizes their benefit.
I don’t like the idea of “give each menu item an icon” being the default approach. This posture lends itself to a practice where designers have an attitude of “I need an icon to fill up this space” instead of an attitude of “Does the addition of a icon here, and the cognitive load of parsing and understanding it, help or hurt how someone would use this menu system?”
The main function of an icon is to help you find what you are looking for faster. Perhaps counter-intuitively, adding an icon to everything is exactly the wrong thing to do. To stand out, things need to be different. But if everything has an icon, nothing stands out.
Shock! Shock! I learned yesterday that an open problem I’d been working on for several weeks had just been solved by Claude Opus 4.6— Anthropic’s hybrid reasoning model that had been released three weeks earlier! It seems that I’ll have to revise my opinions about “generative AI” one of these days. What a joy it is to learn not only that my conjecture has a nice solution but also to celebrate this dramatic advance in automatic deduction and creative problem solving. I’ll try to tell the story briefly in this note.
Concept curators operate in environments where the constraint is not information, but interpretation. Businesses are flooded with dashboards, metrics, reports, trends, think pieces, and opinions. The problem is rarely a lack of data. It’s deciding which signals matter and which can be ignored.
Our profession is learning Both as product developers (in the wider sense of the word), and consultants. The tools, ways, ideas and needs are ever changing. We have chosen to be in school for ever. Welcome! We need to keep learning in the paradigm shift too. But when you do - learn deeper, reflect and think deeply. Use the tool, but focus on the practice. Do the practice but try to understand the principle behind it.
Going forward, we will use traditional settings UIs even less because chat has the potential to become the “meta interface.” It’s both our window into the product and the way we shape our experience with the product — the interface for the interface.
SSE in .NET 10 is the perfect middle ground for simple, one-way updates like dashboards, notification bells, and progress bars. It's lightweight, HTTP-native, and easy to secure using your existing middleware. However, SignalR remains the robust, battle-tested choice for complex bi-directional communication or massive scale requiring a backplane.
This post is about the brute-force reverse engineering of binary (compiled) programs using Large Language Models (LLMs) to automate this two-part problem: decompilation and conversion to a modern programming language.
tldraw, the outstanding collaborative drawing library, are moving their test suite to a private repository - apparently in response to Cloudflare's project to port Next.js to use Vite in a week using AI. They also filed a joke issue, now closed to Translate source code to Traditional Chinese.
Rails-like framework for React, Node.js and Prisma. Build your app in a day and deploy it with a single CLI command.
Create executable demo documents that show and prove an agent's work. Showboat helps agents build markdown documents that mix commentary, executable code blocks, and captured output. These documents serve as both readable documentation and reproducible proof of work. A verifier can re-execute all code blocks and confirm the outputs still match.
All of those things had to be true at the same time. Well-documented target API, comprehensive test suite, solid build tool underneath, and a model that could actually handle the complexity. Take any one of them away and this doesn't work nearly as well.
5206 links collected between and