tin7in

They are not up yet. The Paris one is expected in 2028, the one in Sweden in 2027.

They are building their own infra - south of Paris and another one was announced in Sweden recently.

Thanks for your work and I really really hope the open source project stays maintained. I’ve been using it from the very beginning and it’s been great!

No-one's going to maintain it.

Why? He's going to maintain it and the community is large enough. Another sci-fi idea that's slowly becoming real is that the project is maintaining itself.

OpenClaw is a bunch of projects that evolved together (vibetunnel, pi-mono, all the CLIs). It's even more interesting to see the next iterations, not only what happens to this project.

If you read his blog you’ll find about a lot of his engineering decisions.

Peter was right about a lot of the nuances of coding agents and ways to build software over the last 9 months before it was obvious.

Astro is great and I hope they keep improving after the acquisition.

Given what agents can do, I feel a lot of the sites built on Webflow, Framer and so on will move to code and Astro is a great framework for this.

I partially agree with you that things get abandoned by users when they are too complex, but I think skills are a big improvement compared to what we had before.

Skills + tool search tool (dynamic MCP loading) announced recently are way better than just using MCP tools. I see more adoption by the people around me compared to a few months ago.

This is already in Handy in Advanced > Custom Words.

There is also Post Processing where you can rerun the output through an LLM and refine it, which is the closest to what Wispr Flow is doing.

This can be found in the debug menu in the GUI (Cmd + Shift + D).

I use it all the time with coding agents, especially if I'm running multiple terminals. It's way faster to talk than type. The only problem is that it looks awkward if there are others around.

It has something called "Custom Words" which might be what you are describing. Haven't tested this feature yet properly.

As an alternative to Wisprflow, Superwhisper and so on. It works really well compared to the commercial competitors but with a local model.

Not satire. The author is in denial of what's happening.

I'm really surprised how much pushback and denial there is still from a lot of engineers.

This is truly impressive and not only hype.

Things have been impressive at least since April 2025.

I bought the Refactoring UI book years ago and it taught me so much about simplicity and good design!

Peter's (author) last project is reusing a lot of these small libraries as tools in a way larger project. Long term memory is part of that too.

It's an assistant building itself live on Discord. It's really fun to watch.

https://github.com/clawdbot/clawdbot/

Peter (author) talks more about LLMs as slot machines here: https://steipete.me/posts/just-one-more-prompt

This becomes clearer for me with harder problems or long running tasks and sessions. Especially with larger context.

Examples that come to mind are how the context is filled up and how compaction works. Both Codex and Claude Code ship improvements regarding this specific to their own models and I’m not sure how this is reflected in tools like Cursor.

Speaking from personal experience and talking to other users - the agents/harnesses of the vendors are just better and they are customized for their own models.

For us also Digital Ocean, Render, and a few other vendors are down.

At this point picking vendors that don't use Cloudflare in any way becomes the right thing to do.

I tried it and ran out of credits during the first prompt. No visible way to upgrade or purchase.

Very cool! I'm trying this out for our agents system!

Overall it should feel faster and simpler. We wanted to build a product that lets you focus on your work and not the tool.

You don't need to organize much like in Notion and it should feel less clunky.

The main differences in terms of features are aggregated tasks across the whole workspace, search across multiple tools (Google Drive, Linear), and side by side view.

I'm building Saga which is a fast, minimalist note taking app for notes and tasks.

It focuses on simplicity, speed, and easy linking between notes (autocomplete, referencing, automatic linking).

We have an AI assistant that works inline in your notes. You can select text and rewrite/edit them with Cmd + J.

We also have a chat on the side (Cmd + L) that you can use to chat with your current page or other pages you insert in the context.

The overall idea is that similar to Cursor/Copilot, an integrated workspace is the best UI to work with AI. Workspaces have all our internal knowledge, are integrated with other tools and AI can be used on top of all that context.

We have a free version if you decide to have a look! Looking forward to your feedback!

Saga: https://saga.so is a collaborative workspace with a strong focus on speed/simplicity.

Covid really accelerated this. Friends visiting in Paris are also surprised how fast the city changed in just 2-3 years.

Very cool! Have you looked into call center agents use cases?

Just curious are you using something specific for the tests?

A lot of the popular document/notes/whiteboard apps would use Yjs or Automerge or even a ready solution like Liveblocks.

Not sure about Berlin but in the case of Vienna, social housing and legislation (Mietrechtsgesetz) are big factors. 25% of Vienna’s population lives in social housing which in turn regulates the market.

I’m using (and working on) a note taking app that has bidirectional links and a bunch of other “second brain” features that help me find information quicker.

Since a few weeks I started playing around with embeddings and the results are pretty mind-blowing although it’s just an improved search for now. One unexpected outcome for example is that search now includes snippets with similar meaning but in different languages.