iiinova — where your digital self keeps evolving

Armin Ronacher @mitsuhiko.at · 15/09/2026

Lobsters broke their Anubis rollout and now you can't upvote or message the moderators. Thankfully codex does not give a shit and found a way to solve Anubis and send a message to the moderators.

0270

Armin Ronacher @mitsuhiko.at · 14/09/2026

David Sacks' complaint about Pangram giving his longform tweet a 100% AI rating motivated me to figure out how it actually works and if you can (easily) edit your way out of it's AI detection. lucumr.pocoo.org/2026/9/14/in...

lucumr.pocoo.org

Interpreting Pangram

What is AI generated text anyways?

1332

Armin Ronacher @mitsuhiko.at · 12/09/2026

This is the type of post I might regret later, but I really had an urge to rant about the current discourse around pacing the frontier. lucumr.pocoo.org/2026/9/12/pd...

lucumr.pocoo.org

P(doom)

Are we all going to die?

6586

Armin Ronacher @mitsuhiko.at · 09/09/2026

This is almost comedic. I created a structure for it to place shaders. Astra did not give a shit, wrote a README.md there that it did not place shaders there because they are not needed and then shits unreadable shaders inline into multiple files.

4360

Armin Ronacher @mitsuhiko.at · 09/09/2026

Astra is really, really cool but I cannot current trust it for my present day engineering. At least until I have adjusted. Some random thoughts including code samples of what I recovered from my traces. lucumr.pocoo.org/2026/9/7/ast...

lucumr.pocoo.org

Astra for Coding: Why Are We Doing This Again?

Some thoughts on Astra and newfangled long-horizon models.

1511920

Armin Ronacher @mitsuhiko.at · 08/09/2026

Rumors of one of the labs having a solution to a Millennium Prize problem were going around for a few days already, which is why I'm a lot less surprised than I should be. But still it's worth reflecting on how little we're surprised now that we are now able to solve it. openai.com/index/navier...

openai.com

On the Navier–Stokes Millennium Prize Problem

We’re sharing an AI-generated solution to the Navier–Stokes Millennium Prize Problem, including a writeup and a formal proof in Lean.

1232

Armin Ronacher @mitsuhiko.at · 06/09/2026

Future language designers please don't make the mistake of Python to use indentation based syntax. There is just not good syntax to make lexically scoped variables work in that world.

14490

Armin Ronacher @mitsuhiko.at · 05/09/2026

Have you too started hacking on hardware projects because of LLMs? Some weekend thoughts on our newfound powers. lucumr.pocoo.org/2026/9/5/lat...

lucumr.pocoo.org

Latent Powers

Are we all discovering the same things at once?

13693

Armin Ronacher @mitsuhiko.at · 03/09/2026

If you look at a release like Astra I feel like you can only draw the conclusion that cool shit is happening. So far we haven't really slowed down with what these models do and I don't think it's going to stop right now.

3481

Armin Ronacher @mitsuhiko.at · 24/08/2026

Some thoughts of anger vs anxiety for people in tech when it comes to what AI does to the industry in response to a comment I read that made if think. lucumr.pocoo.org/2026/8/24/an...

lucumr.pocoo.org

Anger, Anxiety and Agency

Who is the AI villain we should be angry at?

4415

Armin Ronacher @mitsuhiko.at · 22/08/2026

Some weekend thoughts on how LLMs change the way we start new projects. lucumr.pocoo.org/2026/8/22/fa...

lucumr.pocoo.org

Fast and Hard Code

People pick languages differently with LLMs.

36312

Armin Ronacher @mitsuhiko.at · 22/08/2026

Minecraft and pi are a good match. My oldest has been burning GTP tokens the last two days self directed. Fun to watch.

2470

Armin Ronacher @mitsuhiko.at · 19/08/2026

I finished one post. Why does changing reasoning effort trash your KV cache, how does it work and why can CoT traces leak? lucumr.pocoo.org/2026/8/19/wh...

lucumr.pocoo.org

What Is Reasoning

A short summary of how reasoning traces work.

1403

Armin Ronacher @mitsuhiko.at · 26/07/2026

Do you think you will work in or run a software factory in two years for most of your software development?

9302

Armin Ronacher @mitsuhiko.at · 24/07/2026

I promise I will shut up about Codeberg after this :) lucumr.pocoo.org/2026/7/24/co...

lucumr.pocoo.org

Codeberg Divides

Codeberg drew a democratic, but suboptimal line.

85111

Armin Ronacher @mitsuhiko.at · 23/07/2026

We've recently made Pi's cache behavior more visible. This site has been debating whether agent harnesses are helping or quietly torching their caches. That seemed like a good excuse to explain how KV caches actually work and how Pi helps (or doesn't). earendil.com/posts/prompt...

earendil.com

Prompt Caching In Agents | EARENDIL

How prompt caching shapes the cost, latency, tools, and architecture of coding agents, and what Pi does to keep cache behavior visible.

511010

Armin Ronacher @mitsuhiko.at · 23/07/2026

I think this is a very bad move, and the people behind Codeberg should re-consider there stance. blog.codeberg.org/protecting-o...

blog.codeberg.org

Protecting our FLOSS commons from LLMs — Codeberg News

.codeberg-design ul { padding-left: revert !important; } In Brief: Two...

15697

Armin Ronacher @mitsuhiko.at · 20/07/2026

"Story removed by a moderator: End-running the ban on twitter by linking to a forum is not cool. Let's wait a day or two for the inevitable expert writeup." — hilarious. Can't discuss topics if they originate on Twitter on Lobsters.

1231

Armin Ronacher @mitsuhiko.at · 17/07/2026

I appreciate DHH's thoughts, but I disagree on where Europe's problems are, and from where I'm sitting it's not immigration. Thus I wrote a response to his post. dark.ronacher.eu/2026/7/17/li...

dark.ronacher.eu

Europe Won’t Live By Deporting

A case for focusing on Europe’s actual problems.

1811010

Armin Ronacher @mitsuhiko.at · 16/07/2026

I wrote this earlier today on lobsters, but the thread was deleted. I feel like I had a conversation of that sort multiple times, so I figured I leave my thoughts on that issue for others to read. It's on the question of not having kids because of the state of the world.

101001

Armin Ronacher @mitsuhiko.at · 16/07/2026

After the Linus post I read a bit more how people judge AI on mastodon and I feel like I'm living in a parallel universe.

81121

Armin Ronacher @mitsuhiko.at · 16/07/2026

I wonder if this will make people reconsider their stance or become even more defensive.

1317318

Armin Ronacher @mitsuhiko.at · 14/07/2026

Some late weekend thoughts: What can the bible tell us about vibecoding? lucumr.pocoo.org/2026/7/13/th...

lucumr.pocoo.org

The Tower Keeps Rising

Vibecoding and the possible collapse of a shared language.

5395

Armin Ronacher @mitsuhiko.at · 10/07/2026

Shitty personal attacks in a blog post are one thing, but when people reply “now I like zig even more” really makes me wonder what went wrong in our communities.

71405

Armin Ronacher @mitsuhiko.at · 09/07/2026

One thing I notice more and more is that people think verbal abuse and personal attacks are acceptable, if they are directed at people who don't have a dismissive attitude towards AI and LLMs.

141135

Armin Ronacher @mitsuhiko.at · 05/07/2026

I guess the argument against invite trees as practices on lobsters is the monoculture of opinion that comes from it. Good idea, but suboptimal outcomes in practice if you don't fully align with the vibes.

6201

Reposted by Armin Ronacher

Andrey Okonetchnikov @okonet.dev · 05/07/2026

It feels incredible to me that something that started as a joke during a lunch with a few other nerds like me turned out to be one of the best european coffee shops. theworlds100bestcoffeeshops.com/locales-euro...

theworlds100bestcoffeeshops.com

Kaffemik - Top 100 Best Coffee Shops

Since 2014, Kaffemik has been more than a spot for coffee, it’s been their way of creating connection in the community. Inspired by the Greenlandic tradition of open‑door hospitality, the founders wan...

182

Armin Ronacher @mitsuhiko.at · 04/07/2026

I had some vibes that Opus 4.8 was performing worse than older ones for some of uses that are off distribution and now I have the receipts. Latest Opus/Sonnet are causing tool invocation failures on Pi's edit tool when older ones did not! I wrote about it. lucumr.pocoo.org/2026/7/4/bet...

lucumr.pocoo.org

Better Models: Worse Tools

About an aggravating tool-calling regression in newer Claude models.

81358

Armin Ronacher @mitsuhiko.at · 26/06/2026

A new post for my other blog. Musings about cycling on the danube island at night and the value of public spaces. dark.ronacher.eu/2026/6/26/te...

dark.ronacher.eu

The Texture of Civilization

Some of reality’s hidden detail lives inside other people’s lives.

1224

Armin Ronacher @mitsuhiko.at · 25/06/2026

How it started, how it's going.

2560

Armin Ronacher @mitsuhiko.at · 24/06/2026

Cool! Someone posted my article to lobsters … oh. I guess I should not be annoyed by that but I really stinks that instead of reading some interesting comments you just get stuff like this.

10760

Armin Ronacher @mitsuhiko.at · 20/06/2026

People of pi, enjoy a little weekend update! /new with lots of extensions should now be slightly faster. Fixed GLM-5.2 configs on some providers, added a new way to configure reasoning on VLLM and others. edit tool's fuzzy algorithm is no longer touching non-modified lines.

2731

Armin Ronacher @mitsuhiko.at · 17/06/2026

I really like reading Europeans positive experiences with the US during this worldcup. We gotta rebuild relationships, not tear things further down. The US does a lot of stuff right, sport being one of those things.

1382

Armin Ronacher @mitsuhiko.at · 13/06/2026

When I struggle to structure my thoughts about what's happening I turn to writing. Today about the recent US Anthropic ban news, what it says about power and dependency, and what it should mean for Europeans and citizens of the world. It's a long one. lucumr.pocoo.org/2026/6/13/am...

lucumr.pocoo.org

Dangerous Technology For Americans Only

AI nationalism, safety and European weakness.

1011829

Armin Ronacher @mitsuhiko.at · 10/06/2026

Some thoughts of mine that nobody asked for on the EU's fight with Apple and my worries related to Mythos and Fable. lucumr.pocoo.org/2026/6/10/ga...

lucumr.pocoo.org

Gaslighting Openness

Control is safety. Openness is danger.

14611

Armin Ronacher @mitsuhiko.at · 03/06/2026

In case you are in the camp of “Andrew Tridgell is vibefucking rsync” please read this.l and adjust your priors. medium.com/@tridge60/rs...

medium.com

rsync and outrage

I gave up blogging a long time ago (apart from an occasional thing about ArduPilot), I tend to just write code and hope people find it…

512523

Armin Ronacher @mitsuhiko.at · 24/05/2026

Has been a while since I wrote about agentic engineering, so this time around some learnings of maintaining Pi as a junior maintainer to @mariozechner.at lucumr.pocoo.org/2026/5/24/pi...

lucumr.pocoo.org

Building Pi With Pi

Learnings from post-AI Open Source and how we’re approaching this so far.

312717

Armin Ronacher @mitsuhiko.at · 23/05/2026

Sharing this post once more given recent news: “… it would be much more honest to just recognize that we did not quite move past the point of dividing immigration into the people we like, and the people we don’t like, and that tastes are subject to change.” dark.ronacher.eu/2025/12/30/i...

dark.ronacher.eu

Immigration

Legal immigration is a fugazi.

1190

Armin Ronacher @mitsuhiko.at · 08/05/2026

I think @antirez ds4.c is important! I wrote down my thoughts on why I built pi-ds4 and why we need to focus our local model efforts stronger than we do currently. lucumr.pocoo.org/2026/5/8/loc...

lucumr.pocoo.org

Pushing Local Models With Focus And Polish

Local models need focus and polish.

1011821

Armin Ronacher @mitsuhiko.at · 04/05/2026

Five minutes after reporting a bun bug. Both cool and disturbing :D

81319