The online whiteboard of Kristofer Palmvik
Yesterday I had something I’d written dismissed as the “work” of an LLM. According to their comment, the reader saw a bunch of emdashes up-front and bailed on the rest of the article. If you can believe it, this was the first such comment I’ve gotten, despite the hundreds of thousands of words — and almost as many emdashes, case in point — that I’ve written over the past few years.
Now, more than ever, I think the best thing you can do is reach out to someone who makes content that you appreciate, and let them know about it.
We believe three things. 1. You should determine how people can reach you. 2. You should decide what your attention is worth - and who benefits. 3. Charging unknown senders a small cost leads to better connections.
– Vi ser AI som ett sätt att göra cirkulär handel enklare och mer tillgänglig. Genom att öppna upp Tradera för AI-agenter vill vi sänka tröskeln för innovation och göra det möjligt för fler att bygga tjänster och upplevelser ovanpå second hand-handel, säger Linus Sjöberg.
Weeknight concerts, new restaurants, maybe a morning swim before work, or simply the feeling that your city has more to offer than the same old routine. Smorgasbord makes it easier to rediscover all of that together with people who are longing for the same things. Through people’s habits, favorite places, and ideas, a new way of discovering the city begins to take shape. More vibrant, more social, and much closer to real life than yet another feed to simply scroll through.
In this new agentic era, the interface itself becomes the AI. Instead of scrolling through a list of posts, we will interact with “agents” that operate at an inhuman speed and scale. These interfaces aren’t just ranking content; they are transforming it—pulling out core ideas, changing their form, and presenting a synthesized version tailored specifically for an audience of one.
A Markdown file an application hosts at its domain — typically https://yourapp.com/auth.md — that tells agents how to register on behalf of a user. It includes which flows are supported, which scopes exist, and how to register for the service.
The transition to the Agentic Delivery Lifecycle is not optional for organizations that intend to lead in the AI era. It requires engineering leaders to make uncomfortable shifts: investing in governance as heavily as features, and valuing a robust evaluation suite as highly as production code.
When Artificial Analysis evaluated K2.5, the model generated 89 million output tokens. The median for comparable models is 14 million. At $0.60/$3.00 per million input/output tokens, the per-token price looks cheap, but when the model produces 6x more tokens per task, effective costs still spike. Kilo Code’s week-long free trial confirmed this: usage surged past 50B tokens/day, and they concluded the model’s verbosity dilutes the savings from input caching. This is the main issue with this model.
The strategy is access restriction — the idea, foundational to Western AI safety since 2023, that controlling a model means controlling its capabilities. Anthropic’s decision to withhold its new model is the purest expression of this logic. But two forces are now converging, making it untenable. Chinese labs are releasing open-source models that match Western closed ones, trained entirely on domestically manufactured chips that the US tried to restrict. And safety alignment — the technical mechanism that’s supposed to make open release safe — is being removed from any model within days of publication, at zero cost, by anyone who can type a command.
In this article, we will explore a technique called "abliteration" that can uncensor any LLM without retraining. This technique effectively removes the model's built-in refusal mechanism, allowing it to respond to all types of prompts.
Henry Ford did not say “If I had asked people what they wanted, they would have said faster horses”. He pretty much said the exact opposite.
Because software is not made by one person in a vacuum. It’s a team sport. Everyone building it needs to agree on what they’re building and why. Believing individual productivity leads to great software is “nine women make a baby in one month” logic. More individual output doesn’t solve problems that require everyone to communicate and coordinate. It makes them worse.
As the pace of software development speeds up, we’ll feel the pressure intensify in other parts of the pipeline: thoughtful design, critical thinking, user research, planning and coordination within teams, deciding what to build, and whether it’s been built well. The most valuable tools in this new world won’t be the ones that generate the most code fastest. They’ll be the ones that help us think more clearly, plan more carefully, and keep the quality bar high while everything accelerates around us.
Every AI provider ships their own bloated client. Different APIs. Different response formats. Different conventions. It’s exhausting. RubyLLM gives you one beautiful API for all of them. Same interface whether you’re using GPT, Claude, or your local Ollama. Just three dependencies: Faraday, Zeitwerk, and Marcel. That’s it.
Dessa självskattningar hjälper dig att reflektera över de krafter som formar ditt inre arbetsliv, de dagliga upplevelser som påverkar din motivation, dina känslor och din känsla av framsteg på jobbet. De bygger på Progress Principle-ramverket utvecklat av Teresa Amabile och Steven Kramer.
Det vi behöver är en plattform. En digital infrastruktur som kopplar ihop människor som vill göra skillnad med människor som behöver hjälp. 58.000 grupper. Tio miljoner svenskar. En app i fickan. Ett organiserat civilsamhälle.
Starting today, we’re upgrading Search with Gemini 3.5 Flash — our newest Flash model delivering sustained frontier performance for agents and coding — as the new default model in AI Mode for everyone globally. Because your curiosity doesn’t always fit into keywords, we’re also introducing the biggest upgrade to our Search box in over 25 years — now completely reimagined with AI. This intelligent Search box puts our most powerful AI tools right at your fingertips, making it easier to ask your questions.
I’ve come to the conclusion though that what people call “pairing” with an LLM is more the illusion of pairing than the real thing. Ultimately, it’s more of a siren than an active collaborator. It’s nothing but your thoughts, reflected back off of a bazillion vectors. That’s not to say it’s necessarily a bad thing, but it’s not the same thing.
Over time, the flywheel produces something that's hard to replicate: structured organisational context. Not a wiki that nobody reads. Not documentation that's perpetually out of date. Living, tested, versioned context that coding agents actively consume and that humans actively maintain. Knowledge that shows up directly in the quality and consistency of every line of code your agents produce.
My personal conclusion can however not end up with anything else than that the big hype around this model so far was primarily marketing. I see no evidence that this setup finds issues to any particular higher or more advanced degree than the other tools have done before Mythos. Maybe this model is a little bit better, but even if it is, it is not better to a degree that seems to make a significant dent in code analyzing.
5286 links collected between and