RumpledElf

@CryptoCamel @TeRry_p @thsottiaux That does not show projects or files, just uncategorised chats. Unless it’s been updated since, everything I use ChatGPT for is missing

@RumpledElf @TeRry_p @thsottiaux “Chat” under plugins in the left menu

Here you are! Thinking I am about to announce a reset. But no. I’m just scrolling twitter and looking for feedback on ChatGPT Work. What should we improve?

@kunchenguid The overengineering is shocking. I found it borderline unusable, all my codebases are simple, I want straightforward stuff done and I was losing far more time getting it to simplify and undo stuff than to actually get work done and it was making me angry and frustrated

after a few more days of using gpt 5.6 sol, i started noticing some issues - if you have good solutions, please share! 1. it uses technical jargons a lot. it's almost speaking its own language that looks like English but you can't understand it until you ask "what do you really mean by this" 2. it can over-engineer and spiral out of control. something that can be done with a few lines of changes can often result in a massive diff fixing everything in the codebase 3. it's overly conservative in terms of touching live environment, so much so that it overly relied mocks for development and validation and build things that don't really work in production these things can likely get tweaked in system prompts, but so far gpt 5.6 is the only model family that don't get these things right out of the box, and it's a bit annoying i love overall how intelligent and fast the model is though! just curious if anyone's run into similar challenges with the model and has good solutions

@thsottiaux Explain what its for? It has chat but you can't access projects or files from the chat. In web, there's really no distinction between work and chat other than some chats are tagged as work. What's it meant to do?

@CryptoCamel @TeRry_p @thsottiaux where? I can't see my projects anywhere in the new codex app

@TeRry_p @thsottiaux Look harder They’re there

@YourFutureCoder @thsottiaux Interesting that those of us who don't like it *really* don't like it

.site? Keep the $100 lol Plus I can't switch to ChatGPT. I have 4 different AI plans from different companies because they all limit me. Now with the 5 hour limit removed I use my weekly limit in a few hours. Doesn't make sense. I'm intentionally not using Chatgpt for most tasks so when no other LLM can help me, chatgpt usually does the trick as it's better for most tasks. So Gemini always wins for me, I almost never hit a limit in the chat or Anti gravity anymore. I'll cancel Chatgpt before any of the other services I use mostly due to the fact I pay the same amount and it works for one day a week.

Or… what if we gave you $100 in Codex credits if you tell us what you love about GPT-5.6 Sol or why you switched? Tweet it, claim your gift, enjoy more usage. First 10k get the free tokens! switch-to-codex.openai.chatgpt.site

@thsottiaux ironically it made me cancel openai and switch to gemini, I can't get it to do what I want

@sumukx Yes, same. I just cannot get it to do simple things. It goes over the top, does a heap of stuff I didn't ask for, and I burn quota getting it to tone it back or redo which really hurts on plus

Some thoughts about GPT-5.6-Sol after ~30B tokens: Sol is the most OCD model I’ve used thus far. It very frequently gets one-shotted by random nits in the codebase and writes a bunch of tests to fix it. Even with fast mode, it’s incredibly slow to do this kind of iterative development, especially when builds take really long. This by itself is not a bad thing, but the worst part is that after 2 compactions, it’s chasing the nitpick / useless goals I never told it to accomplish, rather than the main task. This behavior is so bad, I thought I was messing something up and tried codex, pi, and opencode to figure out if it’s a harness issue, but there is no meaningful difference between the three, which leads me to believe this is a model problem. AI code has this weird delayed release effect. You’ll only notice slop code 2 dev cycles into a codebase when you spend more time fighting with the code and on refactors than on shipping features. It’s possible that sol is better than 5.5 a couple cycles in, but tbd. My file deletion experience has also been similar to others: this is a dangerous model to let loose without guardrails. For instance, when performing a routine container upgrade, it accidentally printed out an env secret, then panicked and rotated ALL secrets (this is internal so not public facing, which was also documented), and proceeded to break everything, spending an extra hour fixing everything and redeploying everything else to use the new secrets. It also gets rid of files it doesn’t like. I have no idea why this is, but I think something about the reward model rewarded bookkeeping. Writing is another problem. 5.6 has a huge context bleed effect. It does not know how to write documentation and starts putting the specs in the documentation. If I ask it to develop a user sandbox for isolation, and also ask it to write documentation, it starts talking about specs and sandboxes in user-facing docs, which makes no sense. Fable is somehow much, much smarter in this regard. Frontend design has also not gotten better. Fable is still one generation ahead here. Overall, as a huge 5.5 user, I am not convinced that sol is a meaningful upgrade. It’s possible my practices need to change, but unfortunately it feels like I’m spending longer fighting with 5.6 than I did with 5.5. It’s like the model is so SO smart, but so hard to work with, compared to fable and even grok4.5 surprisingly. It’s clearly intelligent, but also just doesn’t care about what I ask it to do? (Is this supposed to be AGI feels like?) I hope the codex team fixes what possibly is a bad harness setup, because the benchmark numbers show a very different story from what I’m seeing while using the model.

@samposwal I'm unemployed, I have a gemini and openai sub, its not that expensive. Stacking $200 ones yeah that I don't understand

Genuine Question: How on earth are unemployed people on this platform stacking multiple ai subs and burning through claude/codex api credits? I, with a decent salary, still hesitate before paying for a $20 sub, let alone keeping several of them active.

@ej3mplo @sama Same. I just cannot get 5.6 to do what I ask it. But earlier was fine

Sam, something weird is happening with all your models; because of the way I prompt, I'm never able to get them to do what I need. I've tried other models like Claude or Grok and they actually managed to catch my vibes. I feel like I'm missing out on good models because of this stuff.

still sorta breaks my brain to see our models be good at design finally

@JacobRothfield @AnthropicAI @acccgovau We need an onshore Aussie ai. Can’t be that many of us, shouldn’t need that many data centres right?

@AnthropicAI your company behaves with zero integrity to its customers. My account was banned with no specified reason, then T&S team told me in writing my account was reinstated, but still cannot login and now I’m pursuing a chargeback and reporting it to the @acccgovau

@originalmagneto @sama @SebastienBubeck Heard a lot of people say they prefer codex but there’s just no good business plans so they went to Anthropic

@sama @SebastienBubeck Sam, we don’t have higher sub tiers in chatGPT Business, we feel that we’re being treated with contempt :(

come for the best model, stay because we don’t treat you with contempt

@brucehardy1971 @xoaanya Which is best for just doing what you tell it without going over the top? Luna high seems ok-ish

Is Codex actually better than Claude or does it just feel that way because it's cheaper?

@Michaelzsguo @thsottiaux Claude just has text, no images, no audio. Easier to turn a profit on that

@Michaelzsguo @thsottiaux I mean this is why they’re not profitable

Thank you to the 7M active users who are now using Codex and ChatGPT Work. We have added a banked reset to everyone's account to celebrate the milestone. You can apply the reset in the desktop app or on web and it will replenish the weekly usage for you. Have fun out there.

@59thProfile @thsottiaux Codex users are a tiny percent of ChatGPT users

@thsottiaux 7m? Don’t you have 700m monthly active users? What are you talking about

@KevinTechTalk @thsottiaux @steipete All my chats for work are in projects, they really like to break the projects interface

@thsottiaux @steipete How about fixing regular ChatGPT where I can no longer get to any of my projects or previous conversations without going to web?

Morning. The last 48 hours of Codex and ChatGPT Work have been intense! Three important updates: - Temporarily removing the 5 hour usage limit restriction for all Plus, Business and Pro plans - Rolling out changes that will make GPT 5.6 Sol more efficient across the board and that will be reflected in less usage being used so that it can take you further. Exact impact to be quantified and shared - We hit 6M active users, and are landing a usage reset in the next hour Go do things

@deployfaith @thsottiaux It really does. The world needs more technical debt

@thsottiaux Is the plan to eventually get all the normies vibecoding too? Because it feels like that's the plan.

If you were using Codex before, two things to do 1. Keep using Codex. It is for you 2. Tell your friends and family about ChatGPT Work who you always wanted to show Codex but they’re not as technical and don’t work with code every day and tell me how it goes

Really, really not liking gpt 5.6 so far. Haven’t tried the highest settings but it makes a huge amount of mistakes and it’s burning my quota with all the undoing and redoing :(

@babayagatwt They're waiting. They are already taking huge numbers from ChatGPT

I still can’t figure out why Gemini struggles to compete with Claude and GPT. - Owns Chrome - Backed by Android - Stores most search results - Holds ~95% search history - Google has the biggest user data - Even incognito data isn’t fully private So what’s the problem?

@RiverKhan @thsottiaux yeah codex for work, chatgpt for personal

big points for being transparent + resetting limits whilst you guys are still testing stuff i know you guys spent a lot of time on this merge... but honestly, a lot of us use chatgpt + codex for different things and we LIKE the seperation. chatgpt for me is about personal stuff + what im curious in codex is about building apps + workflows v. different use cases... its weird af to basically access both in the same app. im pretty certain many others of us feel the same way/have similar workflows hope you take the feedback onboard and reconsider this merge!

Hello beautiful people! We have reset usage limits across Codex and ChatGPT Work. And another one will come later in the day. Rejoice. Now that I have your attention, a quick update on ChatGPT Work, Codex and all the updates we shared yesterday. We’ve spent the last 24 hours reading feedback, looking at usage patterns, and talking with many of you. The short version is that there is a *lot* of excitement for GPT 5.6 Sol, ChatGPT Work on mobile & web, but also that we didn't get everything quite right. - We made it too easy to use the highest-compute settings without making the impact on usage limits sufficiently clear. - We reorganized the desktop app in one bold move, making familiar things like chats and projects harder to find. - Our launch framing was focused on ChatGPT Work and to some of our Codex fans it made it feel like Codex was going away over time. Absolutely not our intention, we love Codex and it is here to stay. - And we introduced regressions for some existing multi-agent workflows, alongside a collection of rough edges in plugins and other parts of the experience. We’re landing a first set of improvements today. We’re resetting usage twice so people can keep experimenting, changing defaults and the model picker so they don’t push people toward unnecessarily expensive settings, fixing several plugin submission issues, improving how we represent Codex in the product, and cleaning up some of the most immediate desktop problems. A larger set of improvements will land next week. We’re bringing chats and projects back into the sidebar in a more familiar and customizable way, making usage and reset timing much more visible, clarifying when to use ChatGPT Work and when to use Codex, and addressing the many other smaller pieces of great feedback we've had. The ambition behind this launch hasn’t changed. We think bringing ChatGPT and Codex together into a workspace where people and agents can collaborate is a very important step forward. But an ambitious direction doesn’t excuse avoidable confusion or regressions in the first version. Please keep the feedback coming. We’re moving quickly, and you should see the experience already get better with a few updates today; and substantially better again next week.