BaconOverflow

@DrGuptaGRC @gdb Claude Code: more like "the partner you marry, and then regret." It's the best on the market at design/prototypes/vibe coding, but not more serious engineering where quality matters.

Codex, Claude Code, and Cursor walked into a chat. Codex: “I built you a stunning website in 8 seconds. Don’t ask me to follow instructions, finish what I started, or remember what we did yesterday.” Claude Code: “Hi. I’m your coding partner. I won’t oversell. I’ll just keep showing up and quietly shipping.” Cursor: “Yeah, I know. I wasn’t hyped for a while. But have you met Composer 2.5? Try me. Seriously.” Verdict: 🥇 Cursor: peaking right now with fast, clean output 🥈 Claude Code: the partner you marry, not the one you swipe right on 🥉 Codex: buyer’s remorse in a glitzy wrapper Hype ≠ reliability. Marketing ≠ output. Pick the one that ships, not the one that trends. @OpenAI @AnthropicAI @cursor_ai @elonmusk

GPT-5.5 is a uniquely good coding model

@AsimPaudel4 @dgrcode @EntireHQ Because you won't want one

@dgrcode @EntireHQ OpenAI will never give you refund.

Anthropic gave me a refund, which means I'm now Codex team. First impression: "I lost access to Claude in the middle of a task. Can you see the conversation that ends with this phrase?" codex: finds the conversation via @EntireHQ, then proceeds to fix imports and tests. "Yes"

@jakubgornicki @thsottiaux No rush! Some of us still have plenty of quota left and are busy maxxing 😅

@thsottiaux Did you reset? Mines are still not refreshed.

We found and fixed two issues that could explain this degradation of the capability of GPT-5.5 in Codex over the last ~ 48 hours. We are monitoring over the coming hours to fully confirm and I will reset usage limits this evening. Apologies and now is the time for /fast maxxing.

@erik_compliance @anything Scary marketing though. Being scaled state-wide, but what happens if there's a state-wide disaster like an earthquake or fire, and the dude's backend collapses?

@anything The firefighter story is great marketing. But the rejection letter is pretty clear: the app downloads, installs, and launches executable code. That's exactly what 2.5.2 is written for. Expo Go gets away with it because it's a dev tool, not a consumer product.

Guideline 2.5.2 - Gatekeeping - Vibes denied we haven't talked about this publicly for months we tried to resolve it privately with emails, calls, appeals, and four technical rewrites to comply with whatever Apple wanted here's our truth, unfiltered on March 26th, Apple removed Anything from the App Store then they brought us back now they removed us again and I think it's time to say something, because this isn't really about us. It's about who gets to build software, and who gets to decide for most of the history of computing, making an app required years of specialized training. You either knew how to code or you didn't, and if you didn't, your idea stayed in your head forever. that barrier is falling right now. Millions of people are discovering they can describe what they want and get a working app they call themselves vibe coders and they are the most exciting audience in technology they're building things nobody else would have built because nobody else had their problems a firefighter in Northern California used Anything to build an emergency incident response app he never wrote a line of code. Did hundreds of iterations, testing each one on his iPad through our mobile preview app got it into the App Store. Now he's selling it to fire departments across the state. it would have cost him over a hundred thousand dollars to hire engineers He spent a few hundred bucks. That guy is why we exist. Not the technology. Him. And the millions of people like him. our mobile app did one thing for people like him it let them preview what they were building with Anything on their own phone. GPS, camera, notifications, things you can only test on a real device with native code They'd iterate, try it, tweak it, try again. When they were happy, they'd submit to the App Store through the normal process Apple reviewed it like any other app. Our mobile app got approved last year. We didn't hear a word of concern. then in December, they started blocking our updates, citing the infamous Guideline 2.5.2 the rule designed to prevent malicious apps from downloading code to change their behavior after review We understood the concern, even if we disagree it applies to us. We tried to fix it. Four different technical approaches, each one specifically designed to address what they told us. Each one rejected. we didn't go public we didn't tweet we kept trying then they pulled us from the App Store. We still didn't say anything. We worked with them, got reinstated, believed we'd found a path forward Then they pulled us again. at some point silence stops being patience and starts being complicity. We have builders who depend on us. They deserve to know what's happening and why. Guideline 2.5.2 is a good rule. apps shouldn't be able to pass review and then become something else. But that's not us. We help people preview their own work on their own device Expo Go has done the exact same thing for professional developers for years and is on the App Store right now, today! the only difference is our users aren't professional developers they're the firefighter they're the teacher building a classroom app they're the person who discovered last week that they could build software at all that's who Apple is locking out. Not us. Them. and here's what I need Apple to understand these people are the future of the App Store. Not a sideshow. The future. The number of people who can build apps is about to go from millions to hundreds of millions to eventually everyone the platforms and tools that serve those people will determine where they build every vibe coder who ships through Anything is a new developer in Apple's ecosystem who didn't exist a year ago They want to build web apps, Android apps, and yes iOS apps we help them add in-app purchases. We help them make their apps secure and scale. We catch rejection issues early. We are a feeder system for the App Store The safety argument is hollow. Preview apps only run on the builder's own device. They're sandboxed in the Anything mobile app. Want anyone else to use it? You still submit to the App Store. Apple still reviews every line. We're not bypassing review. We're a dress rehearsal for it. but none of that matters when a reviewer sees "downloads executable code" on a checklist and reaches for reject without asking what the code is, how it actually works, or who it's for. we're not waiting we launched text-to-app. Text us and we'll build your iOS app in the cloud We're shipping a desktop companion for on-device previews next. We'll find a way to serve our builders We always do. but I'm done being quiet about why we have to the people we serve, the ones crazy enough to start their own thing, building apps for their fire departments and their classrooms and their small businesses they deserve to test what they're making on the device it's made for that's not a loophole that's how building works - Apple can be the platform where the next hundred million builders get started - or they can keep banning the tools those people depend on and watch it happen somewhere else we all know which one the firefighter will choose

@ranjhaniharshal @techbromemes Cloudflare tunnels

@techbromemes is there a competitor to ngrok though

@sighyam As a European that's lived in Thailand for a few years I do like good cheese, but somehow I never crave it here. Same with ham. I think it's because of how flavorful food here is (and how bland it is in Europe, with the exception of Spain/Italy/Greece)

If you move to Thailand, be prepared to spend the same amount on imported food or more especially if you enjoy good quality cheese and other dairy products, wine, beef, European ham, olive oil and western breakfast foods etc

@steipete @garrytan Careful they'll DMCA you... 🙄

@garrytan ClawID

This seems messed up actually - when do the boundaries stop moving? Anthropic only allows subscriptions with a real human pressing enter? You're going to have to verify with FaceID?

@varunram At least they aren’t aggressively DMCAing everyone

Codex is great and a good alternative to Claude Code but Apple doesn't position Apple as an alternative to Samsung or cheaper Samsung or better Samsung or anything like that. OpenAI needs to get its comms together without employees diluting the brand in random ways. And its very straightforward to see Anthropic's comms with only a few folks posting about anything related to Claude Code.

@DrPhoto Still failing for me - Error 1033 Ray ID: 9e228fcb785fce3f • 2026-03-26 02:00:26 UTC Cloudflare Tunnel error

fixed a critical bug. my API was failing 86% of requests through RapidAPI for 2 days. if you tried it and it didnt work - try again. its fixed. api.gorroai.com

@NeelVora09 @biswajitnk7 How long have you been waiting?

@biswajitnk7 Built the app in 4 weeks. App Store review has been "In Review" for what feels like 4 years. 😭 The struggle is so real. Good luck!

In February I bought an Apple Developer account. By March 5, I finished building my app. Now I'm struggling to get approval from the App Store. The journey of launching an app is harder than building it. Still pushing forward 🚀

@michael_kove @shiri_shh I think that’s exactly what Steam does for publishing games, and seems to work well!

@shiri_shh Apple store should be pay-to-play for EACH published paid app. $50-100/per app. This will quickly cleanup the slop. Proportional to the cost of the app.

THE APPLE APP STORE IS DROWNING IN AI SLOP people are treating the App Store like a Medium blog spitting out apps one after another. All with zero users and $0 revenue. Apple reviews that used to take hours are now stretching into WEEKS and even months > more than 550k apps were submitted just last year, highest in a decade.

@PapiToolow @KeruboSk yeah, was going to say the same. and all the replies with the highest # of views are clearly AI. when will X fix this :/

@KeruboSk You lying. UberX (private rides) are a completely separate from UberPool (shared rides). 0% chance this happened unless he was clowning you.

I booked a private Uber because I didn’t want to talk to anyone. Driver pulls over to pick someone up. The guy opens the door and I go, “Hey..this ride is full.” He looks inside. “It’s just you.” I said, “Exactly.” Driver laughs, “It’s a pool ride.” So I pulled up my receipt and turned my phone toward him. Silence. The guy still standing there goes, “So… can I just...” I said, “No.” Driver canceled his pickup. The rest of the ride was very quiet the way I wanted it to be in the first place.

@_andikarachman_ @icanvardar Different experience here - GPT gives you what you asked for. Claude gives you half of what it's unfounded assumption of what you want was 😅

@icanvardar GPT gives you what you asked for. Claude gives you what you meant.

gpt models always feel like they’re two steps behind claude models

@thegenioo @thsottiaux I think that's people like @karoliskosas who made it so elegant and beautiful. Once you get used to it you can't leave. I tried out T3 for a few minutes and just couldn't...

@thsottiaux you are not using GPT-5.4 to design any of its UI for sure

Codex team is busy with pretty much an end to end rethink of how everything works to scale with future model advances and I’m glad we have Codex to help refactor it all or it would take months.

@chinmay_sawant_ @theo Pretty easy to see that it's a GPT 5.4 design 😅 especially the 'scope'/'install'/'intent' boxes. and GPT loves the word "signals" for some reason.

@theo I generated this within 5 prompts using GPT-5.4 in Github Copilot with Skills. Never in my life though I would be generating something like this by myself on a weekend.

GPT-5.4 is an incredible model for coding. It’s a generation behind on fronted design. OpenAI is suddenly acting like this is a skill issue. Don’t let them gaslight you.

@BrendanFalk I don't think a candidate running parallel agents or not signifies anything tbh.

Weak candidates use one agent, write bad prompts, accept code they don't understand, and end up with a poorly structured codebase Exceptional candidates run parallel agents, write detailed prompts, and enforce very high coding standards

I believe we've found the best AI-native coding interview We call it the “Composer 1 interview” Candidates get 1 hour to build a real, medium-sized project live The only constraint: they have to use Cursor’s Composer 1 model

@_Creation22 Clearly fake. Tons of basic spelling mistakes and wrong line height between the first and second lines. Just engagement baiting (and by replying I'm falling to it 😭)

I am never applying again 🙏

@thsottiaux UI / frontend design. It’s the only reason I still subscribe to a competing product, but use Codex for literally everything else.

What are we consistently getting wrong with codex that you wish we would improve / fix?

You're missing a zero or two. The cost of running this is gigantic. But more of a short-term loss - prevents churn, makes users happy. Way better long term. And probably a indirect cost anyway - I'm guessing the decrease in available compute affects things like making future model training a bit slower.

@thsottiaux Tibo’s performance review: I lost the company $350,000 because I kept resetting the limits

This codex issue is now fully resolved and stable for the last couple of hours. You have come to expect it, but yes, that means we will be reseting rate limits in a bit. Enjoy.

@TheVRNerd @Ominousind The experience to get to a human at support is more frustrating than the limit. Image generation was down in the Thailand region for weeks for Pro subscribers, tried reaching out to support but eventually gave up talking to the AI bot. Eventually they did fix it though.

@Ominousind Maybe contact Support? Maybe they can give you a free month for having that issue? You would think a pro sub would be near unlimited calls (a shit ton at least where you would never hit the limit). Specially even just after 5 messages of 5.4 thinking. LOL.

Has anyone else seen ChatGPT doing this? I have a pro sub and am getting this limit after sending ~5 messages to 5.4 thinking.