Rison Simon

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.vercel.app

@stephsmithio Same. I switched all of my searches to Google AI mode

Been a longtime ChatGPT user (duh) but feels like it’s been over-optimized into guiding you toward a new question instead of properly answering the question at hand. Just me? Finding my searches migrating elsewhere…

@wesbos @elijahmcom The way elon's promoting cursor seems like he's acquiring x.com/elonmusk/statu…

@elijahmcom I don't think that is set in stone?

Grok's claude competitor is coming Grok build is only available to $300/mo SuperHeavy users at the moment. Anyone tried it? I've been very impressed at the speed/cost/quality of the latest xai models - specifically the speech and image ones.

@danshipper Posthog mcp is also really good. the mcp also has access to dashboard creation tools, so it can create custom dashboards very easily.

using posthog inside of codex it is SO MUCH better to browse posthog inside of codex—codex can write queries and see the results, and it makes our collaboration extremely seamless. codex can also kick off agents that write PRs or run production DB requests to back up insights it's finding a browser inside your desktop coding orchestration tool > an agent in your browser

@TheRohanVarma The problem is that codex is not able to create the design 1:1 from the image

Our 2.0 image model is so good at making screens and vision mocks. Something about AI generated images of digital surfaces feels very “right” to me. Internally, I’ve started seeing tons of product ideas shared and brought to life via image generation rather than prototyping — pretty cool! Using it in Codex makes Codex a full stack design engineer that can build beautiful interfaces. Would love to hear what creative ways y’all are leveraging it for engineering 👀 (This image was one-shot generated with “Make a screen in the Codex App on a Mac desktop that is an AI code review view for PRs.”)

@bentossell Check if your api keys got leaked. Rotate the keys

i dont understand anthropic billing at all... haven't used any agents over the weekend get email receipts all the time dont seem to match whats in my dashboard extra usage is off

@EEEEYHN How are you able to get it to follow the designs so well? I tried making uis with gpt image 2, but the final code doesn't look like it.

Codex 写 prd，调用 Image 2 生成 UI 图， Codex 对着 UI 图直接实现 SwiftUI 代码，配合一点harness技巧 直接神级还原度

@thsottiaux @steipete Create new chats in existing worktree.

It’s the little things that matter, what are some small papercuts you have noticed in Codex? We’ll fix as many as possible in the next week.

@thsottiaux I have a question. Is there a way to create a new chat in an existing temporary workspace, without forking. I want clean message queue.

You can just codex things

@guinnesschen So good and fast. Only thing missing is custom instructions on the written text and custom dictionaries.

You can now use your ChatGPT subscription to dictate anywhere on your desktop now! Have fun!

@thsottiaux Hoping this does better with frontend design too!

Introducing GPT-5.5... together with a ton of new Codex features (more on those in the next hour). Included in all paid plans and coming to API soon. Update your Codex app or CLI to use it. openai.com/index/introduc…

@dkundel @OpenAIDevs Interesting. How often does it take a screenshot of what you're working on? Can we control that?

@RisonSimon @OpenAIDevs That's regular memories! Chronicle relies on memories but you can also use memories without Chronicle. The benefit is that with Chronicle, Codex can augment those memories to contain context on work and tools you use beyond Codex. developers.openai.com/codex/memories

Last week, we released a preview of memories in Codex. Today, we’re expanding the experiment with Chronicle, which improves memories using recent screen context. Now, Codex can help with what you’ve been working on without you restating context.

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.

@embirico Will try it out. One more thing, in the archived chats view in codex mac app, it doesn't show the title of the chat, making it harder to find it. also need search & folder level grouping for archived chats.

@RisonSimon interesting idea! no @-mentioning for now, but you can always just tell codex to go read threads. it knows how to find them

Subagents + steering in Codex is pretty magical. I'm slowly shifting to longer-lived threads. The thread is pretty much always active because I prompted it or an automation pinged it. Then, when I need anything new, I say "using a subagent in parallel, do X"

@braelyn_ai Try codex computer use. It’s pretty good.

pls someone build a better Superhuman i want AI to manage my emails, not write replies for me

@DennisHXu Agree. I’m glad cursor exists. Gives more choice to us consumers.

Cursor's continued success is a very good thing for the rest of the startup ecosystem. Counteracts the (idiotic) narrative that only the labs can win. They also just happen to have the best product — very happy long time customer (almost 3 years)

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.

@signulll It helps two types of users, who are new to setting up permissions and who have a long list of permissions imo. And it's delightful, like you mentioned, we're talking about it.

maybe i am a freaking moron but why is dragging better than just turning it on? every other app just asks you to turn it on & it’s already there. one good reason is that we are all talking about it now, but i can’t seem to figure out the second good reason. dragging is much more of a pain but maybe it feels better psychologically or something? i don’t get it. someone explain this in plain terms to me.