At present the ZCode app from @Zai_org is better than @antigravity app, quite surprised how good the ZCode app is, even though it's a Codex clone, it still has few tricks up it's sleeve.
Wanted to see how other AI model performs for a simple website design based on the same prompt, tested GLM 5.2 and ZCode from @Zai_org, Gemini 3.5 flash with the @antigravity app and also Grok build from @xai
While 5.2 does perform really well, personally I prefer the one created by Gemini. And at this point Grok is just bad, I think it will get better with their upcoming model. Unless you are blocked from using Claude or GPT models, I don't see any reason to use any of these models for development work.
Self-Managed OAuth is now available to all developers on Cloudflare. Here's how we executed a zero-downtime migration of our core OAuth engine to make it happen. https://t.co/toDIp6nQj4
The provided demo is quite interesting, but you know whats more interesting shipping this with @antigravity so people can test it themselves, as a consumer, I find Google's product release decisions quite confusing!
Steam Machine is here, and you can sign up now:
Steam Machine 512GB
Steam Machine 2TB
Plus bundled versions with Steam Controller
Learn more and sign up here: https://t.co/dSr8sbm8db
@SakanaAILabs Love how the names Fable and Mythos became such a pull. Models that barely anyone used and aren't even public still get constantly compared to. Hope they aren't benchmaxxed and actually live up to the claims!
@mark_k It might beat Fable on few benchmarks, at least the 5.6 pro, but man Fable 5 was something else to work with, I don't think 5.6 can match that, GPT 6 could be another story!