@nielr1 From what I've been seeing in agentic builder land, there has been a huge swing towards using the Codex desktop app.
True for me too. Before: 90/10 Claude Code CLI, Codex CLI. Today: 70/30 Codex desktop, Claude Code
I really liked using Canvas before, but this is a nice upgrade.
The iOS copy-to-clipboard feature still has an annoying pre-existing bug: copying does not preserve Markdown syntax. Top-level list item asterisks are the only exception.
The only workaround is to open ChatGPT in a web view and copy from there.
@Dimillian@awwstn One small papercut is that when you're in a Codex thread, swiping back from the left edge of the screen takes you back to ChatGPT, leaving codex entirely. If I'm in the context of working w/ Codex, I'd prefer for it to stay there and just go back to the threads list.
There seems to be a weird interaction between the installed Codex CLI and macOS apps when it comes to available tools. Even w/ both at latest stable.
At first it was the "automation_update" tool, now the new thread tools.
I've tried every combo of latest CLI using npm and standalone installers, as well as the one that ships w/ the macOS app. I just can't seem to get to a state where Codex agents can use the new thread tools, as was the case w/ automation tools the other day (though that's now working).
Which got me wondering: is there a "blessed" or "best" setup when installing and actively using the Codex CLI and macOS apps, so that all the latest features work in both as described?
cc @OpenAIDevs@romainhuet
Anyone else seeing with the Codex macOS app that the thread automation / "automation_update" tool seems to have disappeared / regressed? Previously my agents could set timer-based automations within threads as reminders, but it has seemingly vanished now.
Is 42B+ tokens a lot w/ Codex? โฆalso pretty easy to spot when the macOS desktop app shipped. The CLI's been good, but Codex really shines on the desktop.
Anyone else seeing with the Codex macOS app that the thread automation / "automation_update" tool seems to have disappeared / regressed? Previously my agents could set timer-based automations within threads as reminders, but it has seemingly vanished now.
The Codex macOS app is truly a pleasure to use, so very little in the way of complaints there.
For my use cases, I tend to fire up multiple windows, which is niceโฆbut they're all just named "Codex." That can make some workspace automation and scripting hard.
@romainhuet@embirico it would be awesome if they might be able to carry a name, so that there's more visibility into what's going on in each window!
@thsottiaux Good plan. Good plan indeed.
The one thing that could make it an even better plan might be easing some limits on us poor souls who plow through 100% of their max'ed plan's weekly limit in 3 days. The cause of which is good releases, and one may want to enjoy the subsequent ones.
@0xDesigner Dude, I feel you. Hit my weekly limit today after only 3 daysโฆon the highest tier.
Still love the Claude models, but man the Codex experience has just gotten *so* good as of late.
@whatdotcd Yep! We got the Graco Turn2Me and it's been awesome, very happy with it. Only downside is it's heavier so it's best if it's installed and not swapped between vehicles.
@mronge The connections have all been super solid with it so far. But the biggest thing holding me back from using it a ton has got to be modifier support. The iPad can't handle cmd modifier combos, the Mac version seems to swallow some whole. Hoping it can be addressed!
@cognition Big fan of DeepWiki here, but having some trouble with trying to get a couple of repos indexed today. I've submitted (w/ email) on some repos, and even got the "ready" confirmation but they're still showing as empty. Any way to get them moving along? I can provide the specific ones. cc @dabit3
Just going to have to live vicariously through everyone posting about how awesome the new @OpenAI Codex computer use is while I wait for my usage to reset ๐ญ
@jaredpalmer@github Sick. Just signed up for my outfitter-dev org. I exclusively use stacked PRs today so I'm excited to see how they'd work for my workflows.
1. Big planning process. Once it's well defined, turn them into Linear issues.
2. Use @gitbutler or @graphite to stack branches based on the issues, often 5-10 in the stack, but have done as much as 35.
3. Work up the stack, ensuring each can pass build/test locally and CI independently.
4. Run Codex review on a loop to get all P1's and P2 issues fixed, until it starts spitting out P3's then done.
5. Submit the full stack to GitHub, each as individual branches. Let feedback roll in from Greptile, Devin, Codex, etc.
6. Run my /pr-loop skill which gathers all feedback, dedupes it, associates with specific branches, then feeds it into agents sequentially, from the bottom of the stack up. Fix things up, submit, repeat.
7. Once the feedback gets to a minimum, CI is green, and Greptile says 5/5 on each PR, merge the stack.
Seems complex but it's dialed in w/ just three skills. Can build massive features but not sacrifice review quality with too many LOC changes or files in a giant PR.
I've tried just about every voice dictation app on the market multiple times. @aquavoice is the one that gets my DAU. So stoked it's finally landed on iOS.
@tobi Just submitted four PRs to qmd that together improves chunk identification. Think it would be a step change for handling nested code blocks, lists, and xml tags like those used in agent instructions. More here: https://t.co/fRmiLuf5XA
Lmk if I can help more! Love qmd.