Justin Tyler

@FCB_Cartel @sama This happened to me as well. I gave it a clean set of instructions got stuck in one part of my workflow, looped that that 30 times over the span of 24 hours, came back 24hrs later, nothing useful all garbage.

Codex in the last 3 days has been a nightmare. Hallucination after hallucination, writing so much unwanted code, creating things that are not at all intended, taking too much time and burning tokens unnecessarily. Especially /goal. @sama something is wrong. It burned 50% of my Pro plan tokens for the week in 1 night creating a PR of size 104k lines and when asked about the PR : it said it’s useless and cleared the whole PR and closed it.

@thsottiaux Front-end development, please. Just listen, haha. It’s getting better. Give me a reason to cancel my Claude subscription. Also, under “Business,” I want to be able to purchase premium seats.

For those of you living inside the codex app, what should we prioritize among features, reliability or performance?

@thsottiaux Give me PRO inside of CODEX. Thanks @thsottiaux

We are busy bringing ChatGPT to Codex so that we can bring Codex to ChatGPT. One day this will make sense.

@garymlin It is telling when a company feels compelled to publicly promote how well it treats its employees. A truly strong workplace culture is best validated by the employees themselves, not by corporate messaging.

palantir gave folks 20% if they hit 18 months back in 2017

@thsottiaux This has been absolutely absurd. Do you guys keep a swear meter like Anthropic? Because I’m pretty sure I’m making a serious run for first place.

Codex team is aware of reports of GPT-5.5 performing worse for some users and investigating. We don't have anything conclusive yet and systems are healthy but we will share updates as we go.

@ClaudeDevs I’m wondering whether Anthropic and OpenAI use limit resets as a way to manage compute demand. Like, do they track when most users’ limits reset and then adjust usage windows to spread out demand more evenly?

Happy Friday! We've reset everyone's 5-hour and weekly rate limits.

@OrsatMunitic @thsottiaux This comment needs to be FRAMED. They should be required to read this when they come and go from the office.

Close the loop: native code repository platform, integrated security/Daybreak-style scanning before code is accepted, one-click deploy and dedicated hosting CI/CD, observability, secrets, billing - all built in Basically: idea → code → review → deploy → scale, all under one roof. Every accepted repo becoming quality training data. Oh, and show Linux some love please...

Now that the Codex app is close to being the super app. What should the super duper app do?

@daniel_nguyenx Yep. Noticing same issues.

Codex is basically unusable for me today. Stuck at thinking... forever. I'm afraid that it will be the next Claude Code soon 😭

@trq212 "Sorry could not complete your task, an asteroid took out our space computer"

Claude in Space 🤞

@ClaudeDevs Reset limits and I’ll stay

Usage limits are up, effective today we're: 1) Doubling Claude Code's 5-hour limits for Pro, Max, Team and seat-based Enterprise plans 2) Removing peak hours limit reduction on Claude Code for Pro and Max plans 3) Substantially raising our API rate limits for Opus models

@thsottiaux There is an issue where if I exit a thread, and come back to it, if its on auto or full access, where its looses touch with its permissions and just starts asking me for permission for everything.

Last week, we released *Auto-Review* mode in Codex! It is now the default within OpenAI and reduces amount of approvals needed by ~200X. Amazing work from our alignment team. Read the blog at alignment.openai.com/auto-review

@sama Fix this first. And before you ask, I'm running fiber gigabit internet. So it's not me.

i would like to talk to people who have built amazing things with 5.5 that weren't possible with earlier models. i am especially interested in examples that took ludicrous token budgets. thanks.

Failed to connect to browser-use backend "iab". No Codex IAB backends were discovered. Discovery diagnostics: listedPipes=2, candidates=4, browsers=0, iabBrowsers=0, failures=["discovered/get-info/string","discovered/get-info/string","legacy-iab/connect/object","legacy-chrome/connect/object"], pipeListingError=none. @thsottiaux Why does this happen every single time I ask Codex to use browser.

@gao_zibo All of this and more is coming

Watching this drop is so sad. @OpenAIDevs

@OpenAIDevs King George from Hamilton. He deserves his crown.

Show us the Codex pets you hatched. Use /hatch to create your own Codex pet. We’ll pick 10 favorites to get 30 days of ChatGPT Pro.

@sama @official_taches You could just let us pay to reset our own limits. Instead of giving us free resets (which we still enjoy), just allow us to pay like $50 to reset. Im no business man, but $50 is better than free resets.

@official_taches what do you need for just one plan?

I’m a doctor 🥹

Gold: MedKit by Bedirhan Keskin from Türkiye A voice-based clinical simulator where medical students take histories, order labs, diagnose, and get scored on their reasoning against the latest published guidelines. youtube.com/watch?v=6bN6hn…