EL

Thanks for all the new follows! My best trading advice: 💎 Focus on the HTFs. They will simplify things a ton 💎 Get good at identifying the draw on liquidity 💎 Some things will come ONLY with experience. Be patient 💎 Losses are normal & the only armor for it is risk mngt

@thsottiaux 1. Reliability 2. Performance second 3. Features third

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

@Rasmic Dude it’s lighthearted fun … it’s not that serious

It’s important to stay humble. This is not the way.

@abraham_keleta @TheAmolAvasare My sentiments exactly! The long explanations are needless if the comms at Anthropic were much better. It’s always a knee-jerk response after the fact. Makes everything that’s being said now meaningless. I don’t know why it always has to be when they’re found out. Smh.

@TheAmolAvasare you guys keep reacting to stuff instead of proactively communicating. Why is it hard to come out and say we are testing something and give a heads up before someone, inevitably finds out? It's pretty consistent theme that is super obvious to many users. Just do that one thing

For clarity, we're running a small test on ~2% of new prosumer signups. Existing Pro and Max subscribers aren't affected.

@DavidOndrej1 This coming from the guy who’s bashed GPT models consistently … the internet is a weird place. Glad to see you’re finally a believer

OpenAI's Codex is the most powerful coding agent I've been using it non-stop for the last year And compiled everything I learned into a 94 min video, enjoy

@thdxr @Rasmic I was just thinking the same thing 😅

@Rasmic bruh how many apps do you use x.com/Rasmic/status/…

guys i can't stop using opencode... opencode is great

@LLMJunky Also, from the videos I have watched, I half expected it to be housed in the automations section and not in the project folder. Seems a bit weird to me.

@LLMJunky a little help here please. sorry if this is a noob question but are my automations supposed to appear under my project folder on each run? My Upskill automation has run 2 times and each time in a different thread.

@Ai_Vaidehi @grok does Open AI have a similar program, or a partner program?

Anthropic just announced the "Claude Certified Architect" program. And you can start today. In 16 years of my professional career, I haven't done a single certification. Not one. Not AWS. Not Azure. Not Google Cloud. Not PMP. Not Scrum. Not any of the alphabet soup. I learned by building. By breaking things. By shipping. But I'm about to break that streak. I'm going for my first-ever certification: Claude Certified Architect — Foundations Here's why this matters — especially if you're a developer, engineer, or any professional who feels like the AI wave is moving too fast. Claude Code launched a few weeks ago. And it feels like a paradigm shift. Not an incremental upgrade. Not another chatbot wrapper. A fundamentally different way of building software. Agentic architecture. Tool orchestration. MCP integration. Context management at a systems level. If those words sound intimidating — that's exactly why this certification exists. It covers everything from agentic orchestration to prompt engineering to Claude Code workflows. Not surface-level content. And here's what got me: It costs nothing. Free. Zero. $0. So if you've been feeling left behind... If you've been watching others ship AI agents while you're still figuring out where to start... If you've been telling yourself "I'll learn this next quarter"... This is your sign. Stop scrolling. Start building. First certification in 16 years. Let's see how this goes. Links in the comments 👇 Cc : Brij Pandey

@danshipper @PaulSolt thought you might find this interesting. how are you handling these issues in your workflow?

this is what my codex chat history looks like. we absolutely need a new UX for coding agent guis a few thoughts: 1. my usual workflow is i have one main chat where im doing all my work for the day and then separate windows for each individual issue / feature. once those are in good shape and reviewed, i send them to my main chat to qa on staging and deploy 2. the "main chat" paradigm is nice because i want one place to have a good idea of "here's everything i need to accomplish today, what's been done, and what hasn't"—but right now it's at the same level of prominence in the UX / priority as every other chat which isn't great. 3. the main chat "orchestrator" should also be able to easily know what's going on in other threads. i need to be able to reference other chats easily and also have each sub thread have some idea of what the others are doing by default (should be able to isolate if i want though) 4. it's pretty wild to be doing your n-th codex run of the day, type what you want, and then have the model be like "okay, let's see what's going on here, ahhh there's a repo, and it has X features..." as if it has no idea what i've been doing that day. seems like a huge waste of time and tokens, we need something better by default.

@LLMJunky @TheNasdaqer 😂😂😂 yep

@TheNasdaqer @_eltrades @thsottiaux hes trading tokens now

QQ for @thsottiaux or anyone on the team who knows... Does GPT 5.4 consume additional plan usage per token than 5.3 Codex considering that it had an API price increase?

@thsottiaux The key part of that tweet is ‘for a while’ lol. The demand for Codex is insane right now so chances are we have another spike in a few days

OK, Codex is back and stable and we should be good for a while. Reset button pressed, should see it in a bit

@thsottiaux @OpenAIDevs @OpenAI this is getting pretty annoying insid of the Codex app. Please fix this asap.

@jacob_posel Never hit the 5H limit. But hit the weekly twice, and each time in just 3 days. What am I doing wrong?

A lot of people saying this is too expensive/eats too many tokens. I pay for the Codex Pro Plan ($200/mo). I use GPT-5.4 on the Codex app. I have agents running at least 12-14 hrs a day. Often multiple simultaneously. I am yet to run out of tokens.

@thsottiaux @OpenAI @OpenAIDevs Please fix this. Its negatively affecting dev work. And the rate refresh Tibo mentioned ... err ... not reflected on my Pro account at all.

@thsottiaux @OpenAI @OpenAIDevs tokens are running extremely quickly while using GPT 5.4 in Codex. And NO, I am NOT using /fast. Never had this issue with GPT 5.3 Codex. I got a second Pro account cos I couldn't wait for weekly limits to refresh, and its running just as quickly.

@thsottiaux @Sauers_ By the way, I’m on a Pro Plan. And my usage in the last 48 hours with GPT 5.4 is nowhere near what it’s been with GPT 5.3 in the past - and I never hit the weekly limit

@thsottiaux @Sauers_ @thsottiaux this needs to be fixed. My weekly limits are done and exhausted, but the 5H limits are fine. I’ve never ran out while using 5.3 codex heavily. Switched to 5.4 (no fast) and exhausted my weekly limit for the first time ever.

On a Plus subscription, I'm using about 1% of the Codex limit every 4 seconds

@thsottiaux There's definitely an issue somewhere. Codex telling me my weekly rate limits have been used up. But inside ChatGPT with the same credentials, still no issues using the same models. Weird

We have found one issue that leads to some users seeing inconsistent usage across sessions but it is quite rare, affecting less than 1% of users. We are working on a mitigation and continuing the investigation. For the rest we are not seeing evidence of higher usage consumption other than the advertised token cost increase of GPT-5.4 being 30% higher than GPT 5.2 and GPT-5.3-Codex.

@steipete @nakulsinglla @grok what are acp subagents in the context of this post?

@nakulsinglla acp subagents are lit

Hey Peter, @steipete you've used Codex a ton, and now you're at OpenAI — any quick tips to really maximize it for coding? Been finding it definitely better than Claude lately (no more handholding/charade BS), but want to squeeze even more out of it. Any tips?🦞