P
85 posts
i wouldn’t say ChatGPT Atlas is a failed product, the technology is now powering the insane browser use in the Codex app
Kartik@code_kartik
Does anyone remember ChatGPT Atlas? Seems like a failed product to me. Never installed it and never even tried it.
English
@robinebers I think we should all just default to using gpt-image-2 to ideate and then 5.5 to implement. I asked image-2 to gimme 3 ideas, all were really good. Here's one for example.
English
what AI model designed this?
Opus 4.7 of GPT 5.5?
🫠
English
Show us the Codex pets you hatched.
Use /hatch to create your own Codex pet.
We’ll pick 10 favorites to get 30 days of ChatGPT Pro.
OpenAI Developers@OpenAIDevs
Customize your Codex pet with /hatch
English
I swear if you're seeing this you should seriously try GPT 5.5 on codex and Images 2.0. They're essential life tools at this point
Leon Lin@LexnLin
Done. Codex and images 2.0 cooked
English
@thsottiaux Sorry for posting this here but please something needs to be done to consolidate concepts. I just went to hell and back with figma. Long story short, I learnt the app connector on chatgpt and the mcp are very different things. Codex does some voodoo that wormholes chat apps to it
English
You can now keep codex going for days.
With GPT-5.5 it will build an entire OS kernel for you if you ask, or find critical bugs in a codebase, or optimize your database schemas, or… the options are endless.
Felipe Coury 🦀@fcoury
/goal also lands in Codex CLI 0.128.0. Our take on the Ralph loop: keep a goal alive across turns. Don't stop until it's achieved. Built by my co-worker and OpenAI mentor Eric Traut, aka the Pyright guy. One of the GOATs I get to work with daily.
English
OpenAI’s GPT-5.5 is the second model to complete one of our multi-step cyber-attack simulations end-to-end 🧵
English
@yacineMTB OpenAI had the best model since GPT 5. Its been kill me how X has been promoting Claude all these months. Opus 4/4.1 did me dirty. I don't care about vibes, I care about correctness and working solutions.
English
@basedjensen Surprised how many are realizing this now. Opus 4/4.1 helped me refactor a monolith to micro-services in 2 weeks. I spent the next 1 month using GPT 5 to undo the trash. Thats when I moved to GPT for all work.
English
Fucking Claude keeps breaking two thing for every one thing it fixes. That's it I am switching to 5.5
English
@fabianstelzer Opus is the king of sycophants. At least GPT disagrees with me sometimes while providing me alternatives. Opus just does whatever I ask it to, and badly because it leaves too many loose ends.
English
Nonsense. We are going to need software engineers for years to come.
AI Edge@aiedge_
Anthropic CEO (Dario Amodei): "Coding is going away first, then all of software engineering." What do you think about this?
English
Clarifying the last bit of my article:
> we need US AI labs to build frontier, large, open source models.
> Google is the only lab with a strong open source strategy, but they are focused on small, edge-hardware models, not what enterprise needs.
> the US labs also need to make their closed source models much cheaper.
> if we don’t, US enterprise will build on Chinese AI.
This is not about having the most intelligent model, it’s about having the cheapest and best “workhorse” model - the model for 99% of use cases.
Matthew Berman@MatthewBerman
English
what are you building with codex?
Paul Solt@PaulSolt
What app are you making this weekend with GPT 5.5 and Codex?
English
