Ala Eddine

@antirez @championswimmer the irony, Dario is Italian….

What Europe should do right now: 1. Call all the European researchers working on AI and return them back with same salary (or they can stay but switch career). 2. Fill EU places having GPUs with money, and put those people there. 3. AI partnerships with China + India.

Is it time to boycott Anthropic? At least OpenAI contributes GPT-OSS, Alibaba releases Qwen, Mistral releases OSS models… why do you guys keep paying a company that gatekeeping the technology they didn’t even create? They nerf model without notifying, you keep paying They nerf usage on the same plan, you keep paying They senser everything most of LLM related questions and cyber defense, medical research, you keep paying Gatekeeping the harness, you keep paying Most expensive inference, you keep paying....

Google and Nvidia and XAi injecting billions of dollars into Anthropic literally killing competition, chinese doing ok even with restricted access to top tier GPU, but nothing at the scale of Anthropic, this company is made into a monster, and a reminder they been using this model internally for months, europe can’t compete, can’t even get close… it’s a money game.

I want to say a final thing about my Fable first reaction: I dedicated my life to programming and I'll use every innovation in the field, also to extract value and bring it to the local inference world, to Redis, and so forth. But:

@DannyLimanseta It's another fine-tuned kimi right?

Very impressed with Composer 2.5 after about a day of usage. I've almost moved over to it exclusively from GPT 5.5, even using it for planning now. It's like Opus 4.7 on steroids, crazy fast. Fast models really get me into the flow of building, which is exhilarating. Also, a sneak peek of a weekend mini-project I'm building: a racing game where you race your mouse cursor.

@Baconbrix @rounak what about swiftui preview is it possible to bring that to codex?

You can now 'inspect element' for any iOS app directly in Codex or the browser! ~ / npx serve-sim S/O @rounak for the contribution 🚀

@rounak @nick_candello @Baconbrix how?

@nick_candello @Baconbrix It will work for SwiftUI too!

@Baconbrix @rounak only react native app or work with swiftui?

Every AI company is shipping its own VS Code clone with a new name—Codex, Claude, Cursor… same core, just stripping away editing. Feels like they don’t want you to edit anymore 😄

A fork for $60B, no foundational model, only the autocompletion model? And a fork?! What am I missing here? It's not even the best harness…

@Dimillian why we don’t have computer use in France…

I guess I’ll more stuff to write and talk about Codex and Swift soon 👀

@ComfyUI How do they make these transitions? Give us the template.

Seedance 2.0 is now live in ComfyUI for everyone. This state-of-the-art model brings us one step closer to production-quality video generations.

@zeeg So you are using Claude code to vibe code Sentry?

anthropic being down, rate limits, etc is understandable. huge hardware reqs and insane growth. claude code being bug filled is just a result of people vibe coding slop at anthropic and accepting it as ok. it is not ok you will lose your customers just as fast as you've gained them.

@ivanfioravanti which harness?

This weekend I'll use GLM 5.1 only for coding 💪 So far so amazing good 🚀

@Dimillian works for iOS apps?

@krispuckett @openclaw @claudeai Using GLM 5.1 since yesterday; not bad. I still ask my OpenClaw agents to delegate coding tasks to Claude Code CLI and Codex.

Anyone else using @openclaw with Codex? How is it compared to @claudeai ? Seriously considering canceling Max plan now.

Just open-source it. It’s not like the Claude model weights—it’s only the harness. Open-source Claude Code and let the community participate instead of having the flicker for a year now.

@theo how much money this add cost them ?

We don’t talk about this enough. Opus scored 20% higher in Cursor than in Claude Code.

Ill keep using openclaw not only for multi agent but for freedom, the good models already closed source, I don’t want my agents to be behind Claude walls.

@bcherny @michalbrojak @trq212 more context makes model performance worse, or I missed an episode?

@michalbrojak @trq212 Never

What??!! 1M tokens context window?? Insane. Thank you Claude ❤️ But, when to clear it? @trq212 or @bcherny any tips?

Openclaw voice done! setup in the first comment