reesh

@_justcarlson @cheikhshift @benhylak what features?

@cheikhshift @benhylak It lacks some pretty useful features present in most harnesses. But for me, it’s fine. The model is what makes it shine.

i'm sorry but codex cli is just unusable. i actually like the model.

@reach_vb @ajambrosino we need an openai .curated subagent lib pls

@ajambrosino subagent*

@mweinbach It's available in Enterprise right now. I'm using it.

Skills beta soon for ChatGPT Pro Pls OpenAI, sooner than soon I beg of you

@alxfazio should have made this a skill

@DominikTo @thsottiaux @SIGKITTEN it has steer now

@thsottiaux @SIGKITTEN ChatGPT desperately needs "Steer". Using ChatGPT after using Codex is like not being able to interrupt someone when you already know what they are going to say (or where they are going wrong). Torture. 😅

openai should just replace chatgpt with codex

@dylan522p literally has all of these things damn you're dumb

OpenAI Codex 5.4 + CLI sucks Lazy as fuck and slow, it just uses my local files, tries to make up an answer from that rather than creating something Doesn't have plugins like this github.com/jarrodwatts/cl… No /statusline to auto config my status bar either #cost-and-duration-tracking" target="_blank" rel="nofollow noopener">code.claude.com/docs/en/status…

@ShishirShelke1 Apple maps is better because it doesnt have this

Yeah the debate is over. Apple Maps is cooked.

@anothercohen Built something similar not even an eng i like ur UI library what did u use?

@dsp_ @signulll you were saying?

This is so cool and ... it is an MCP App.

@NickADobos Stop condition, task list, ways to check work and iterate. mine goes for hours

GPT 5.4 brings back GPT 4's lazy coding Except now instead of "// ... rest of code here" We get "This ___ is the next step would you like me to do it?" Yes bro... you have a whole planning doc we discussed for 300k tokens. just do it. ralph loop needs to be in codex app NOW

@GamersNexus @PatrickMoorhead this is the lowest IQ shit i have ever heard

@PatrickMoorhead If you used tokens and AI, you did not, in fact, "personally build" it. Millions of people whose work was stolen built it. You benefited from it.

I had a good friend tell me the apps I created were trash because I didn't have a formal database. I took that as a challenge. In 5 hours, I personally built, populated, and deployed a database containing all the content the company and analysts created over the past 15 years, press quotes, and social media posts, with integrated semantic and basic search and auto-updates. And is scalable to 10x the data. Tested it with 1,000 different queries that users would make. It works. :-) Now it's time to connect the apps I created with embedded data to the new database. It cost me around $200 in tokens. Ironically, the most expensive part was scrubbing ten years of press quotes. Still a better deal than Meltwater or Muckrack. The next step is to inject proprietary and protected data into it, with proper safeguards and attribution.

@heynavtoor @PietroMontaldo That is a pretty retarded assumption

@PietroMontaldo the pattern matters more than the specific model. if it happened with GPT-4 it can happen with any version

🚨BREAKING: OpenAI told you every update makes ChatGPT smarter. Stanford proved the opposite. GPT-4's accuracy on math problems dropped from 97.6% to 2.4% in just three months. And nobody told you. Researchers at Stanford and UC Berkeley tracked ChatGPT's actual performance over time. Same prompts. Same tasks. Different results. The model that nearly aced math questions in March was getting them wrong 97 out of 100 times by June. Code generation collapsed too. In March, over 50% of GPT-4's code ran perfectly on the first try. By June, only 10% did. Same questions. Dramatically worse answers. Every silent update OpenAI pushed made the product you pay $20 a month for quietly worse at the things you actually use it for. The researchers tested GPT-3.5 and GPT-4 across math, coding, medical exams, reasoning, and sensitive questions. The drift was massive and unpredictable. Some tasks improved. Others fell off a cliff. And there was no way for you to know which was which, because OpenAI never disclosed what changed. Here's where it gets personal. If you used ChatGPT for code in March and it worked, then tried the same thing in June and it broke, you probably blamed yourself. You thought you prompted it wrong. You tried again. You wasted hours debugging your own questions. But it wasn't you. The model had silently changed underneath you. OpenAI's VP of Product went on X and said "we haven't made GPT-4 dumber." Stanford's data says otherwise. 97.6% to 2.4% is not a matter of opinion. Every business building on ChatGPT's API, every student relying on it for schoolwork, every developer using it to ship code is standing on ground that shifts without warning. You trusted it yesterday. It changed overnight. Nobody told you. You're not imagining it. ChatGPT is getting dumber. Stanford proved it.

@_simonsmith I would have think they should bring this to canvas

Love this and want something like it in ChatGPT Enterprise. Working with docs right now in groups that include humans and agents is too cumbersome. I just want to have ChatGPT make a doc, share it with a colleague, now the three of us are jamming on it, comments and suggested edits and changes attributed appropriately. Like a ChatGPT group chat, but for documents.

@ryancarson how do you review all that

I've shipped so many PRs today because of this. 1,251,678,004 tokens in 24 hours. Bonkers.

@signulll apple music one is good

i’m curious, do ppl use apps inside of chatgpt? if so, which one & what’s the use case? i haven’t explicitly used an app at all yet nor have i come across gpt prompting me to use one. also the directory doesn’t seem updated since launch.

@Degen_CPA this is how i get shredded

i ate 7 cheese sticks and drank 4 diet cokes today

@kayintveen @marcelpociot been enjoying a screen of 6 pop out codex app windows better than the CLIs

@marcelpociot GUI wins for one focused agent you're watching. CLI wins the moment you want 5 running while you do something else. the bottleneck isn't the interface, it's your attention budget

Nobody can convince me that the CLI experience for AI agents is better than using a proper GUI 😅 That's just impossible

@ryancarson @alex_frantic @linear what monitor is that ryan

This is how I run 5 agents concurrently in a Code Factory to write/ship 100% of our code. It uses Symphony from @alex_frantic (oss) + Codex Mac app + @linear Took me 2-3 days to set up and now it’s *cranking* github.com/openai/symphony

@nicdunz 5.4 expensive; cant give to free users

wait so why did they release 5.3 instant and not 5.4 instant

@petergyang @ysu_ChatData @tomkrcha peter can you use this for ios apps?

@ysu_ChatData @tomkrcha Yeah just try it yourself honestly it’s free- pencil.dev

Watching 6 AI agents design an app together genuinely blew my mind. In my next episode, @tomkrcha (CEO of Pencil) showed me: → Swarm mode: Spinning up 6 design agents → How it all works under the hood (JSON?!) → How to design inside Cursor & Claude Code 📌 Subscribe to get the full episode tmr: @peteryangyt?sub_confirmation=1" target="_blank" rel="nofollow noopener">youtube.com/@peteryangyt?s…