vber retweeted
来一个Antigravity 亲测的排雷指南:
1. 卡登录页进不去?
直接开全局/Tun 模式!还不行就切日本或新加坡节点。
2. 一直显示 "One moment, the agent is currently loading..."?
方案A:点右上角设置左边的 Open Browser 开扩展 -> 登出 -> 彻底重启软件 -> 重登。
方案B:关掉所有 Chrome 窗口 -> 再点 Open Browser。(我是通过这个成功的,玄学)
方案 C:什么都不干,过一会也能加载出来
3. 提示 "Model quota limit exceeded" 没额度了?
别慌,假警报!在 Gemini 3 Pro (High) 和 (Low) 之间来回切就好了。
4. 提示"Agent terminated due to error"?
太火爆了,应该是真的炸了😂让子弹飞一会儿
vber retweeted
I'm giving away Claude Code for FREE.
Yes, you read that right -- the world's best AI, now completely FREE.
My mission is to get the next billion people to write great software. I believe EVERYONE should have access to the best AI, but so many are constrained by costs.
I'm solving this by:
disrupting the world's fastest growing industry = AI
+ with the most proven business model = Ads
You can actually try it out now -- just one line of code, and you unlock all the powers of Claude Code, for free.
how it works:
1. sign up on Giga AI Free
2. change Claude Code env variables to use our inference endpoint
2. to support the free usage, we'll add ads inside the AI responses (only contextual and relevant ads, no spam)
Since we get too many signups, there's a waitlist, but we'll be rolling it out to the maximum people as we can.
Watch the video to get started & comment and retweet to get access first.
vber retweeted
Looking forward to the EU and UN holding Cambodia accountable for attacking civilians in Thailand
I normally don't touch geopolitics but as I'm getting fresh updates from Thai sources, I will report some factual information for English X.
Cambodia opened fire on Thai civilian areas today, generally in the Si Sa Ket region, and it appears deaths have already occurred as a result.
#กองทัพบก
The most inconvenient thing in Terminal mode AI programming tool is to restore checking points. #geminicli #claudecode
84
#augmentcode augment code这2天总是出现503,要不停的输入“继续”才能完成任务。The Augment Code has been showing a 503 error these two days. You have to keep entering "Continue" to complete the task.
2
2
540
vber retweeted
Claude 3.7 Sonnet is worse than 3.5, and I'm happy to see it's not just me.
It's over-confident. It ignores rules. It unnecessarily does more than it needs to do and therefore breaks the code.
It drove me crazy these days. I'm going back to 3.5.
Amazing! I just calculated my bone weight, which is 4.2 liang (a traditional Chinese weight unit). Want to know your future holds? Try the calculation yourself at cg.vber.me #FortuneTelling #fortune #destinyreading #destiny
2
105
用Cursor做了一个浏览器插件,实现将选中的文本转换为图片卡片。
I developed a browser extension using Cursor that converts selected text into image cards.
#BrowserExtension #Cursor #ImageCard
127
#Claude 我宣布Claude 3.5 Sonnet编码能力全面超越ChatGPT 4o。视频演示了生成效果,在约15分钟内,通过4轮对话,Claude成功完成了以下任务:
1.编写一个页面,展示两个MySQL数据库中的所有表格
2.标记出数量不一致的表格
3.提供完整的Python后端代码和前端实现。



















