David Molina

@thsottiaux Hey, i dont know what happened, had the reset yesterday as you said but this morning it was back to what it was and displays that limits will reset the 3rd of june. Is this a bug? Anyone having this problem too?

The Codex usage limits have been reset for all paid ChatGPT subscriptions. You should be back to 100% weekly and 100% hourly limits. Let the tokens do incredible things today and have fun.

@NicolasZu Really fed up with all this benchmark propaganda that ai has brought with it…

You cannot rank Muse Spark, Sonnet 4.6, GLM 5.1, Kimi K2.6 above GPT-5.5 and be called a serious benchmark website

@thsottiaux Windows app with native harness (powershell) just keeps writing strange characters and mojibakes

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 Please fix mojibake in windows app...

Have you tried GPT-5.5?

Hot take: GPT5.5 is nice but not nice enough to justify its 2x price. #GPT5 #spud

#GPT5 #SPUD

@anxietymsgs Wait you are getting likes?

Would y'all keep tweeting with 0 likes???

@adahstwt Just behind that same feature but in mac

is this the best thing Apple has ever created or is there anything better?

@LLMJunky So we are not talking about that arcanine now?🫣

Look ma new Codex Updates! 0.119.0 and 0.120.0 are here. And with it, a HUGE number of quality of life updates and bug fixes! > Hooks now render in a dedicated live area above the composer. They only persist when they have output, so your terminal stays clean. If you're running PreToolUse or PostToolUse hooks, this is a huge readability win. > Hooks are now available again on Windows > CTRL+O copies the last agent output. Small but clutch when you're pulling a code block into another file or chat. > New statusline option: context usage as a graphical bar instead of a percentage. Easier to glance at mid-session when you're trying to gauge how much runway you have left. > Zellij support is here with no scrollback bugs. If you've been stuck on tmux just because Codex was broken in Zellij, you're free now (shout out @fcoury) > Memory extensions just landed. The consolidation agent can now discover plugin folders under memories_extensions/ and read their instructions.md to learn how to interpret new memory sources. Drop a folder in, give it guidance, and the agent picks it up automatically during summarization. No core code changes needed. This is the first real extension point for Codex's memory system, and it opens the door for third-party memory plugins. > Did you know, you can /rename a thread? But what's really cool about that is, after you rename it, you can resume it with the same name, no more UUIDs. codex resume mynewapp or directly from the TUI: /resume mynewapp > Multi agents v2 got an update to tool descriptions More reliable multi agent environments and inter agent communication > You can now enable TUI notifications whether Codex is in focus or not. Modify this in your config: [tui] notification_condition = "always" > MAJOR overhaul to Codex MCP functionality: 1. Codex Tool Search now works with custom MCP servers, so tools can be searched and deferred instead of all being exposed up front. 2. Custom MCP servers can now trigger elicitations, meaning they can stop and ask for user approval or input mid-flow. 3. MCP tool results now preserve richer metadata, which improves app/UI handoff behavior. 4. Codex can now read MCP resources directly, letting apps return resource URIs that the client can actually open. 5. File params for Codex Apps are smoother: local file paths can be uploaded and remapped automatically. 6. Plugin cache refresh and fallback sync behavior are more reliable, especially for custom and curated plugins. > Composer and chat behavior smoother overall, resize bugs remain though. > Realtime v2 got several significant improvements as well. > You're still reading? What a legend. 🫶 npm i -g @openai/codex to update

Might be a dumb question but… why can’t we get OpenAI OAuth in cursor? Would be amazing with the new 100$ plan.

@YanitedWarrior @malagojr Yes, if you are used to the models output you can tell if one writing is ai or not. My point is that all those “AI Detectors” webs are basically scams.

BREAKING: Don't copy and paste answers from ChatGPT. ChatGPT writing is easily detectable. Use these prompts instead and see the magic:

@Still_learner Bet

I'm blowing small accounts If you're under 50K reply and I'll boost you 🚀

@thdxr Sign up your ass in project glasswing then

just got penetrated by mythos

@LottoLabs Why everybody praising GLM Coding Plan? Am i the only one still getting bullshit output and infinite loops from it?

If I had to buy one coding plan It would probably GLMs right now

@0xSero Doesn't really help if zai's api keeps being the worst GLM provider... GLM 5.1 can't even read tool output in cursor...

I’m trying to test something! How many of you would pay for Cursor Pro if Cursor let you oauth with GLM (ZAI) Leave a like, comment, and share. If you’re interested.

@cursor_ai Cursor shipping like crazy lately isn't getting the hype it deserves...

Cursor can now attach demos and screenshots of its work to PRs it opens. Your team can review artifacts created by cloud agents directly in GitHub.

@RaminNasibov Mythos too expensive lol

Why are AI startups still hiring humans?

@Steezehuman Yeah imagine without X premium

Small accounts tweeting to absolutely ZERO engagement

@elonmusk X chat is really buggy most of the time...

Use 𝕏 Chat for messaging and voice/video calls. Comes with this great benefit of actual privacy.