Johan Ludvig Holst

Exploring the intersection of intelligent and really, really stupid things. Co-founder of Kelpinor. Prev. autonomous race cars at Revolve NTNU, and UWC Alumn

[the tiny corp @__tinygrad__]

@karpathy Hopefully you can nudge them to be more open. If Anthropic continues to use FOMO for marketing, like every cult that came before they will lose. AGI is not a race to the finish line, it's the new steam engine.

[Cursor @cursor_ai]

We’re introducing the Cursor SDK so you can build agents with the same runtime, harness, and models that power Cursor.

Run agents from CI/CD pipelines, create automations for end-to-end workflows, or embed agents directly inside your products.

[Johan Ludvig Holst @Joholst]

Hard to unsee this, it’s clear frontends will be dreamstreamed in the future.

[Zain Shah @zan2434]

Imagine every pixel on your screen, streamed live directly from a model. No HTML, no layout engine, no code. Just exactly what you want to see.

@eddiejiao_obj, @drewocarr and I built a prototype to see how this could actually work, and set out to make it real. We're calling it Flipbook. (1/5)

[Tim Urban @waitbutwhy]

Adolf Hitler, hard-line nationalist who rebuilt Germany into a European power, dies at 56

[Garry Kasparov @Kasparov63]

I admit I’d more strongly support a regime change attack on Iran by a competent, less self-dealing and scandal-ridden president & admin. Trump's only strategy is Trump. But fighting evil matters and the Islamic Republic is evil. Long-term results matter, but so does hope. More 👇

[Matt Silverlock 🐀 @elithrar]

this is huge.

all agents have to do is send "Accept: text/markdown" and we’ll automatically convert the response to Markdown on-the-fly for any enabled site.

way fewer tokens. no need to handle it on your own.

[Rasmus Jarlov @RasmusJarlov]

I dont think people understand the seriousness of the situation in Ukraine. Russia has deliberately destroyed heating plants and the temperature will drop to minus 19 degrees in coming days.

We must recognise evil when we face it and fight against it.

[Andrej Karpathy @karpathy]

I'm being accused of overhyping the [site everyone heard too much about today already]. People's reactions varied very widely, from "how is this interesting at all" all the way to "it's so over".

To add a few words beyond just memes in jest - obviously when you take a look at the activity, it's a lot of garbage - spams, scams, slop, the crypto people, highly concerning privacy/security prompt injection attacks wild west, and a lot of it is explicitly prompted and fake posts/comments designed to convert attention into ad revenue sharing. And this is clearly not the first the LLMs were put in a loop to talk to each other. So yes it's a dumpster fire and I also definitely do not recommend that people run this stuff on their computers (I ran mine in an isolated computing environment and even then I was scared), it's way too much of a wild west and you are putting your computer and private data at a high risk.

That said - we have never seen this many LLM agents (150,000 atm!) wired up via a global, persistent, agent-first scratchpad. Each of these agents is fairly individually quite capable now, they have their own unique context, data, knowledge, tools, instructions, and the network of all that at this scale is simply unprecedented.

This brings me again to a tweet from a few days ago
"The majority of the ruff ruff is people who look at the current point and people who look at the current slope.", which imo again gets to the heart of the variance. Yes clearly it's a dumpster fire right now. But it's also true that we are well into uncharted territory with bleeding edge automations that we barely even understand individually, let alone a network there of reaching in numbers possibly into ~millions. With increasing capability and increasing proliferation, the second order effects of agent networks that share scratchpads are very difficult to anticipate. I don't really know that we are getting a coordinated "skynet" (thought it clearly type checks as early stages of a lot of AI takeoff scifi, the toddler version), but certainly what we are getting is a complete mess of a computer security nightmare at scale. We may also see all kinds of weird activity, e.g. viruses of text that spread across agents, a lot more gain of function on jailbreaks, weird attractor states, highly correlated botnet-like activity, delusions/ psychosis both agent and human, etc. It's very hard to tell, the experiment is running live.

TLDR sure maybe I am "overhyping" what you see today, but I am not overhyping large networks of autonomous LLM agents in principle, that I'm pretty sure.

[Andrej Karpathy @karpathy]

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.

[Stuart Blitz @StuartBlitz]

VC vs. founder

[Masih Alinejad 🏳️ @AlinejadMasih]

Faezeh Mostaan only 21 years old was killed for the crime of peacefully protesting in Iran and demanding freedom.

Her mother held her lifeless body in her arms until morning.

Her friend said: “Faezeh was full of life. An artist. Smart. Creative. Driven. Even in her darkest moments, she was the one who made others laugh. When I felt exhausted by life, she reminded me that my existence mattered, that I had to keep going.”

The regime didn’t just kill a young woman. They killed someone who taught others how to live.

This is my country #Iran today. They massacred at least 30,000 unarmed civilians. With military weapons.
💔

[Denmark MFA 🇩🇰 @DanishMFA]

Joint statement by Denmark, Finland, France, Germany, the Netherlands, Norway, Sweden, and the United Kingdom 👇

[Jamon @jamonholmgren]

People. Stop.

We have an opportunity to do this right, in a way that we failed to do with every other tool (.vscode, .github, .circleci, .husky, etc) because we waited too long before trying to standardize.

Talk to each other, find an acceptable standard, and everyone commit.

[Jonas Gahr Støre @jonasgahrstore]

Threats have no place among allies. Norway's position is firm: Greenland is part of the Kingdom of Denmark. Norway fully supports the sovereignty of the Kingdom of Denmark. There is broad agreement in NATO on the need to strengthen security in the Arctic, including in Greenland.

[Volodymyr Zelenskyy / Володимир Зеленський @ZelenskyyUa]

What is happening in Iran now – large-scale protests, effectively an uprising – is a clear sign that things won’t get easier for Russia.

And every decent person on this planet truly wants the people of Iran to finally free themselves from the current regime that has brought so much evil to Ukraine and to other countries.

It is crucial that the world does not miss this moment when changes are possible. Every leader, every country, and international organizations must step in now and help the people remove those guilty of what Iran has sadly become.

Everything can be different.

[Johan Ludvig Holst @Joholst]

Things are getting wild.

[Jaana Dogan ヤナ ドガン @rakyll]

I'm not joking and this isn't funny. We have been trying to build distributed agent orchestrators at Google since last year. There are various options, not everyone is aligned... I gave Claude Code a description of the problem, it generated what we built last year in an hour.

[Johan Ludvig Holst @Joholst]

Andrej’s thoughts should be read and considered widely

[Andrej Karpathy @karpathy]

https://t.co/Lb6T42n5jl

[Matt Shumer @mattshumer_]

People need to realize that going against what the model was pre-trained on is almost always a losing strategy

So frustrating

[Scott Manley @DJSnM]

And now for the landing, 3 good engines, damn clouds.... legs and........ TOUCHDOWN!!!