y_qecea

@tuturetom @LexnLin

正式开源 open design 的落地页和全套设计风格 Skills 🚀 人人都可以做世界级的 PPT 和落地页！ 浓缩一套顶级审美的生图和样式风格，涵盖最佳实践，杂志级美学和大师级动效 💥 落地页、Web 原型、PPT、简历、作品集、长文档、信件等所有格式全支持🔥 可在任意 code agent 中使用，无需任何设置！

@corbin_braun nah unfollowed this slop poster

opus 4.7 just one shotted one of the best frontends I have seen in a long time

@MrAhmadAwais OS Command code + website I hope?)))

@y_qecea also open source coming soon :)

Founder POV: Should we open source Command Code?

@dharmeshba @opencode which OS model is best overall? deepseek v4 pro seems to be better than kimi 2.6 in everything except frontend and multimodality, what about qwen 3.6 and glm 5.1? how do U rank them in real work

Claude rate limits suck! Just get @opencode Go plan for $10 and use Kimi 2.6 Lit 🔥

Opencode x Deepseek v4 pro x High gives you 800 million tokens at only $10! This is a solid option for personal projects at the Claude Opus 4.5 level. You can go even better with Kimi K2.6 x opencode Go plan for $10/month. That's Opus 4.6 level

Antigravityファミリークォータ改悪の件、家族に話しました。 途端に泣き崩れる家族。 すまんな、もうGemini 3 Proは使えない。 今から家族にクォータがめちゃくちゃ渋い事、伝えます。 Antigravityのファミリークオータで生活している人もいるんです。俺はGoogleを絶対に許さない。

@MrAhmadAwais yes please

Who wants to beta test a $1/mo coding agent Go plan we’re launching at Command Code next week?

@LyalinDotCom @geminicli sorry but Google is behind competition x.com/i/status/20495…

If you're not using @geminicli to do code reviews of your project (assess its architecture, spot bugs, etc), you're missing out. It's so good at this. I use Gemini 3 flash all the time in this way, it tends to be really spot on and damn fast even over a large codebase.

google antigravity just went missing bro

🚨 🚨 🚨 EMERGENCY FOR FAMILY MEMBERS IN GOOGLE SUBSCRIPTION FAMYLI QUOTA FOR @antigravity IS NOW SHARED FOR ALL FAMILY MEMVERS IT MEANS FOR 6 PEOPLE IN FAMILY = 1 LIMIT, NOT SEPERATE LIKE IT WAS BEFORE I already closed @GoogleAI Ultra sub and moved to @ChatGPTapp Pro sub.

@GoogleAI @antigravity @ChatGPTapp PLEASE DO MAXIMUM REPOST AND SHARES, THEY THOUGHT THAT THEY CAN DO IT SILENTLY

I am not sorry, I am canceling @GoogleAI Ultra subscription. it's nearly usable with current opus limits in @antigravity. 250$ per month for AT LEAST 30 minutes of work with one decent model. gemini models is the very bad. I am done with that, moving to inf limits to @ChatGPTapp

@ayushsoni_io please give tutor on exposed Grid and boxed layout landing pages

new landing page unsiloed.ai

@zeke second insane design skill, now I got in collection fully ready nothing design + Swiss design

I made a Swiss International Style design system as an agent skill. npx skills add zeke/swiss-design-skill swiss.ziki.boo

GPT 5.5 thinking is interesting but it is too expensive in the real world. Opus 4.7 is dead on arrival PREDICTION: The new Gemini will become the most used model by the end of May

I'm speechless at Google signing a deal to use our AI models for classified tasks. Frankly, it is shameful. For HR, I'm not speaking on behalf of Google but in my personal capacity, quoting public information from a well-sourced article of a reputable publication

Codex > Claude Code: - limits - coding model - nice team - computer use - more stable app, still has some flaws and performance issues tho Claude Code > Codex: - UI gen

I have three major issues with Gemini. I hope @GoogleAI is listening: 1. Coding: Antigravity with Gemini 3.1 Pro is weak compared to Codex and even to Opus 4.7, which is also very weak compared to Codex. 2. Gemini AI Studio's missing usage tracking for a given API key. Why introduce many keys if not for tracking the usage per key in order to optimize the pipeline? 3. Recitation error in OCR/information extraction use cases. You submit a cover image of a document and ask to extract the title and the list of authors, and the request is rejected for copyright violation. This is just crazy. Information extraction is THE major use case for vision LLMs. You can do better, @GoogleAI.