Maralc

Cannot wait until opensource AI catches up with frontier. Sooner or later it will happen.

Unbelievable

And of course we've got Omarchy on board as well. Fast operating systems and fast race cars just go together beautifully!

@tiredkebab @dhh I created a fork of the repo and updated it to the latest Omarchy version. Will keep updating and maintaining. github.com/maralcbr/omarc…

@maralcbr @dhh Hi there! GitHub has suspended my account recently due to unknown reasons. I’m in touch with them trying to to recover my account. Please allow me some time. Thanks.

What happened to the Omarchy Mac project on github? Tried to update today and it says repo doesn't exist anymore. @tiredkebab @dhh

@Kappaemme1926 The halving of the quotas on Jun 1st.

If you use Codex daily, what’s your biggest complaint right now?

@AMDRyzen Unfortunately memory bandwidth will still be too slow for any real AI application (circa 273Gbps)

AMD Ryzen AI Max PRO 400 Series processors are coming to Ryzen AI Halo platforms in Q3. Built to support a new class of local AI workloads, Ryzen AI Halo is designed for more agents running in parallel, more intelligence operating locally, and systems that reason and adapt in real time.

@tiredkebab @dhh Any progress recovering the account? Maybe we should tag someone from github here?

@thsottiaux Respect

We found and fixed two issues that could explain this degradation of the capability of GPT-5.5 in Codex over the last ~ 48 hours. We are monitoring over the coming hours to fully confirm and I will reset usage limits this evening. Apologies and now is the time for /fast maxxing.

Hey @thsottiaux Codex + GPT 5.5 is really dumb since yesterday. Something changed in a very bad way. Codex Feedback Id: 019e2998-f2eb-7480-b9f9-3bb146ffee3b

@thdxr @thsottiaux

something is going wrong with gpt 5.5 caching doesn't look like much on this chart but this it's now using 2.5x as many input tokens as a week ago and dropping

@thdxr I felt it got a bit dumb in the last 2 days. Not great.

Sounds like a great opportunity to try it out.

@0xSero This has been very painful

Codex nooooooo I can't close this popup

@thsottiaux Would be great to be able to work remotely in a linux server like we can do with VSCode.

What are we obviously not getting right with Codex?

@theo I am seeing a few posts questioning why we don’t have higher contexts in codex for at least pro subscriptios like they offer on the API. I see a lot of contexts being compacted in long running tasks, which should affect performance.

It's so hard to describe the vibe difference between Opus 4.7 and GPT 5.5 (for coding) GPT is smarter and can unblock you, but it gets stuck in stupid ways and strangles itself with context sometimes. Opus will go down the most insane paths and refuse to acknowledge obvious answers, but it understands intent better and has more taste. Whenever I use one for more than an hour, I always reach to the other to "clean up". Best part? All of this changes every few weeks 🙃

It works after the latest updates. Thanks a lot!

Hey @thdxr - It would be great if opencode could support mac screenshot copy and paste into opencode (+ghostty). I saw a discussion and a PR for it but the contributor was shot down for not being vouched.

@LexnLin Maybe a bit off, but in your opinion what is the best way to create brand logos with AI?

ask me anything about vibecoding/frontends I'll answer every question :)

@gabrielchua Can we please have one in Brisbane?

Good morning, Sydney - Codex

@kimmonismus This is just because Apple is about to release the M5 version. There is an Apple event on the calendar already.

Apple’s M4 Mac mini lineup is becoming increasingly hard to buy, with all 256 GB variants now unavailable at the Apple Store and even higher-storage models facing six- to ten-week delays. However, this goes to a broader supply chain strain rather than a simple product transition. The situation reflects industry-wide shortages of memory and storage components, alongside Apple’s apparent decision to prioritize higher-demand MacBooks over desktop units. tl;dr ongoing semiconductor supply constraints are causing more and more problems.