Alex Burdiyan

@Hal_Wayland @kai_fell Odin mentioned. I reply and like automatically. More people should know about Odin.

@kai_fell Odin is an obvious correct choice when choosing a C alternative at this point

the author of Zig needs therapy

@nicopreme @dillon_mulroy @uwukko Although I could say that I find the various LLM integrations in Surf a bit confusing sometimes. Seems like the tool is trying to do too much, instead of just being browser automation tool.

@nicopreme @dillon_mulroy @uwukko I was going to post this. I've had much better success with surf than agent-browser. I guess mainly because it's using an extension instead of debugging protocols which some sites seem to be able to detect and make your life hard.

what’s the best tooling to let agents use a browser rn? agents always seem to burn a ton of tokens using things like agent-browser esp using helium (@uwukko maybe you have some good guidance here?)

@thsottiaux Merge it properly first :) The ChatGPT app is Codex and Work first, ChatGPT later which is confusing and annoying. There isn’t even a global shortcut to start a ChatGPT chat inside the ChatGPT app. I honestly like it better separately, and I still use ChatGPT Classic.

Now that we merged ChatGPT and Codex, what should we merge next? What's the double or nothing move.

@thsottiaux No 5h limit and banking resets is pretty perfect. In an “ideal world” there would be no limits :)

We've had no 5h limit in Codex plus and pro for a few days. Do you think it is better or are you finding it difficult to manage the usage included in the weekly limit effectively? If we were to make this different, what should it look like in an ideal world?

@thsottiaux @TokenGremlin Please! I got so used to having full access to ChatGPT via desktop app, and the global shortcut for quick chats. The new update castrated the ChatGPT interface on desktop so heavily 😅.

@TokenGremlin ChatGPT Chat Hmmm. Yes yes. I see.

I just declared a moratorium against AI-written change descriptions (e.g. PR and commit messages, also issues/tickets) from my team. AI was writing change descriptions that were worse than useless to me as I tried to review PRs: outlining details of the code that could easily be seen by looking at the code, but omitting the higher-level framing needed to understand broadly what the code is doing. I think people like having AI write these things because the output looks structured and thorough, which makes it feel professional in a way. But this isn't actually valuable. Concise, high-level descriptions are better for everyone. If I need to use my own AI to interpret what your AI wrote then something is wrong. Let AI write code, sure, but for the description, I'd rather see your prompt than your output. We could maybe have extended agents.md with guidelines on writing descriptions, but this seemed a bit pointless since a good, concise change description only takes a few minutes to write -- not a significant time savings to delegate to AI. At least, it doesn't take long if you understand the code -- and if you don't understand the code, then I'm definitely not merging it.

@mitsuhiko Truly, the lack of minivans on European market is so sad :( Who in their sane mind have thought that the SUV is the ultimate family car? I could never understand that. XC90 is a great SUV though, so congrats :)

We finally got the new car but I’m a bit sad that we’re leaving the minivan life behind. But there are just no nice options on the European market right now that work for us. So now it became a Volvo XC90.

@TheGreenCedar @thsottiaux What reasoning level are you using in 5.5?

@thsottiaux I didn’t get to try 5.6 yet, but as of 5.5, codex cannot in any realm write human-friendly documentation. It leaks its instructions and inner monologue straight into readme files and frontend widgets. It’s terrible

What is something that you feel is surprising that Codex still can't do well and we should have gotten right a while ago?

@thsottiaux 1. Keep /side chats around, don't throw them away. I sometimes want to do a side chat, but then get back to it after I close it. I couldn't find a way to do it. 2. Group forked chats in the sidebar into a tree. 3. Let me create a chat on a connected machine in the same project.

If you want to know why this does not die: EU countries are majority in favor of it. So the EU parliament can’t kill it. Because it would be EU legislation the countries can blame it on the EU because they know it’s unpopular.

I was finally able to build me a simple screen recording app that I was dreaming about — something that @Apple doesn't bother to do. I always wanted the simplicity of shift+cmd+5, but producing small files, not the behemoths that macOS spits out. It took just a few prompts.

Finally got invited to glaze.app by @raycast. It's pretty cool what they are doing there!

djb (@hashbreaker) told us about an NSA employee who showed up on the IETF TLS mailing list for the first time ever. Their one and only vote: weaken encryption. 🤦‍♂️ The NSA lost the last vote, so now they're packing the next one and we need YOU to help us beat the NSA! Full conversation in the thread 👇

@thsottiaux Sandbox config got broken apparently. I have extra writable sandbox roots in the config, to avoid approvals every time a command accesses ~/Library/Caches, and it works in the CLI but not in desktop app. Used to work before.

What should we improve in the Codex app. What's not delightful?

Getting gaslit by AI is funny. I had to explain Codex something it got terribly wrong, and after compaction it said — "Great, you are getting it right this time" as if I had the issue 😂.

@zx_loro Which provider are you using?

kimi 2.6 thinking > gpt 5.5 low 🤨

The Siri/EU situation is a regulatory masterpiece. Apple cannot launch Apple Intelligence in the EU. Why? Because under the DMA, if Siri gets deep system access, every other AI assistant must get the exact same. Anything less would be unfair competition. A gatekeeper privileging its own service. So either Siri ships and every Shenzhen startup, Cyprus shell company, and nephew hackathon project gets identical root access to 450 million Europeans’ digital lives or nothing ships. Apple proposed a “Trusted System Agent”: a security intermediary so third-party assistants get capabilities without ripping the phone wide open. The EU rejected it. Magnificent. Apple’s response: fine, then no developer APIs either. No Apple Intelligence, no third-party integrations, no foundation model access for EU developers. The entire layer simply does not exist on this continent. Excellent. This is the path. Why depend on American AI when we can build the entire stack ourselves? A European foundation model, trained on a European GPU cluster, running on a European OS, on a European phone, manufactured in a European fab, powered by European nuclear plants we have spent fifteen years closing. Estimated time to ship: 2047. Estimated cost: the GDP of three member states. Estimated outcome: a chatbot that requires a cookie banner before each response. Worth it. In the meantime, European users are protected from Apple processing data Apple already holds by ensuring nobody processes anything at all. Not a bug. The intended outcome. Regulatory product design with a sledgehammer, swung with precision. 🇪🇺

@wcools @andreaskweber Is the document data model of Thymer documented anywhere? Curious to learn more. I guess it’s in general a lot richer (an probably more rigid at the same time) than what Markdown can do? Or is there really a clean bidirectional mapping between Thymer and Markdown?

@andreaskweber @burdiyan It’s quite a bit different from syncthing because the idea behind the mirror and the app sync engine is to map local file edits to crdt-like operations / real-time collab

The best API is no API. Instead of MCPs and CLIs, Markdown Mirror will let agents edit state directly through files while the app translates those changes into multiplayer operations behind the scenes. Files as the API.