Won the Vibe Code Camp challenge 🏆 The challenge: do something cool with an 8-hour transcript. So I built an app to grab speaker workflows, search insights, copy agent skills, and quiz yourself Appreciate the free year @danshipper 🤝 Link: vibe-code-academy-every.verc…

I avoided worktrees for months because they seemed unnecessarily complex. Turns out I was wrong. Now I can test 3 different product flows at once without touching my main codebase. Here's how I got worktrees working with @convex in codex. (works with claude code too) I started by asking codex to research the setup. Told it to check both codex and convex docs and come up with a plan. Codex created a script for setting up the worktree, and copying over the relevant env vars. First hiccup: codex was using outdated convex cli commands. I had to manually copy the new commands from convex's changelog and ask codex to use that. Without this, it created overly complicated scripts. Second hiccup: I didn't realize I had to manually select the new environment for each worktree. Once I figured that out, the setup script ran automatically. For convex specifically, I needed to set a specific node version for it to run locally. But that was it. I also set up portless by @ctatedev and Vercel Labs so that each worktree has its own website. It works beautifully. Just need to create a branch in the worktree, and portless will create a URL with that branch name. Another reason worktrees worked for me is using @better_auth . Because each worktree can run fully isolated, each one keeping its own login state in the local convex. It’s beautiful. Now I can test different product concepts without touching my main deployment. Everything runs locally. No extra costs. Worth the setup time.

Just had a holy shit moment with codex computer use. I asked it to archive all newsletters from my Missive inbox. Took some time but got through everything without errors. I've tried multiple AI inbox tools before. None come close. This uses the actual app on my mac. Way more powerful than I expected.

I don't get the Opus 4.7 hate. Ya, it's more expensive with the new tokenizer. But performance wise? It's solid. I've only used it in @cursor_ai till now and it's been fine. Maybe it's just a claude code issue.

Anyone got this update yet?

I'm adding 🟡 to Codex thread titles just to track which ones I'm still working on I don't love archive. It hides threads completely. I just want active ones on top and archived ones visible below, separated. How is everyone else managing this?

What happened to @GroqInc?

Who do I need to tag in @convex to get a response?

They got me.

2016: what if Google builds your idea 2026: what if Anthropic builds your idea

Hey @waynesutton, I upgraded to Convex starter plan and all my referral bonuses disappeared. That shouldn't happen right? Can you help?

Why does Codex cli have /compact but the mac app doesn't? I don't want to start a new message at 90% context window. Right now I'm opening codex cli just for this.

Codex $20 plan is unusable now. Hit the 5-hour limit twice today. It's day 2 after the reset and I've already burned through 50% of my weekly usage. This wasn't happening before. Way worse than expected from ending the 2x promotion.

Codex read @posthog's source code, understood how it works, and found an undocumented function to fix my issue. Worked because posthog's mcp let the agent check my actual data while debugging.

PostHog does LLM observability now and it's better than most dedicated tools. Helicone got bought by @mintlify, so I needed an alternative. I tried Portkey, but it's ai gateway was missing some new models, so I thought to try @posthog one, and first impression is really great

I don't open Activity Monitor anymore. Mac overheating? Ask AI what's draining battery. It checks system processes and tells me exactly which app is the problem.

Why is Sora still the first recommended skill inside Codex?

I get website reports and signup analytics delivered to iMessage every morning. Screenshots included. Zero effort after 10 minutes of setup. I'm using @interaction (Poke) with @posthog mcp and it's one of the few places where mcp actually makes sense. Top referrers, conversion data, all formatted and sent to my phone. I don't even open PostHog anymore unless I need to dig deeper. Now I'm experimenting with managing todos through it too. There's a format called XIT that keeps everything in a single file, perfect for agents. It connects to my calendar and manages my schedule. Still testing the workflow, but it's working. Too many non-technical users are setting up OpenClaw for basic actions and making it way harder than it needs to be. Poke is a managed service that just works. Use that.

I work 10x more than I used to. And it actually feels fun. I had 5 years of struggling with discipline. I tried every article, every productivity system, every meditation app. None of it stuck. What helped me the most? A relationship where I'm happy and supported. And so many of the problems I used to obsess over just... disappeared. I've literally forgotten what most of them were. Turns out I didn't have a discipline problem. I just hadn't found the right person yet.

Cursor's cloud agents are where they can really out innovate everyone right now. But two things are holding it back. Each request burns multiple credits, it gets expensive fast. And you can't switch models mid-message, which is the one thing @cursor_ai does better than everyone else. They built the best multi-model UX in the industry and then disabled it in the product that needs it most.

Cursor cloud agents are genuinely impressive. But each request burns multiple credits. The screenshot speaks for itself. @cursor_ai should let you bring your own Codex subscription. Imagine if that's possible.