AI Agent 实战玩家，分享日常心得、技术干货、随想感悟与个人看法，不涉及宗教政治，也避免无谓争论。 Telegram: https://xitter.gq/t.co/vLt2eTfh56 https://xitter.gq/t.co/GIdMOUgXxq https://xitter.gq/t.co/qn6nmey2Gt
Joined September 2022
- Tweets6.1K
- Following3.2K
- Followers3.5K
- Likes1.6K
这个可以看你的推文被限流的情况，挺方便的，转需
Under the Hood now shows you which posts received a visibility-limiting label, making it easier to see what’s affected: xitter.gq/i/jf/under_the_hood
This was a top request — thanks for the feedback.
You’ll see the specific posts listed when fewer than 5% of your posts during the report period have that label.
ALT Screenshot of X's Under The Hood feature, showing a list of posts that have a given label.
早上看一新闻: 通用汽车非法出售驾驶行为与位置数据，支付 2.2 亿美元达成和解
国内的车企，驾驶行为和位置数据都是默认共享的吧😂
reuters.com/business/autos-t…
Programming is dead
Engineering is not
一言不合就自己搞，真羡慕，太牛批了
现在的 AI 浏览器，个人用起来都没有特别顺手的，于是我自己写了一个，叫 Kaze，日语里是风的意思。内嵌的AI它的操作就像风一样的丝滑&不会干扰你。
Github: github.com/jackwener/Kaze 欢迎大家star关注。通过issue反馈问题。
项目主页：kaze.build
项目核心插件已开源：github.com/jackwener/Browser…
浏览器本体的代码还在梳理之中，未来会开源。
最大的亮点应该是它的浏览器操作非常丝滑、尤其是在double Deepseek的情况下。
AGENT 干活的时候在后台另开一组标签，按任务命名。
浏览器本身可以作为MCP接给自己的Agent用，也可以直接使用浏览器内嵌的Agent。
未来还会持续改进。
Github: github.com/jackwener/Kaze
OpenAI 到底在干嘛？
2026下半年最让人困惑的2个公司：OpenAI 和 Kimi
最悲催的公司：智谱
最惊喜的公司：Google、DeepSeek
最渣的公司：A/
Kimi 开创历史，只重置25%，看来是真缺卡😂😂
We're sorry for the rate limits and unnecessary quota consumption on the K3.1 Pro subscription plan. These were our issues, and we should have fixed them sooner.
Today, every subscriber on every plan gets a one-time usage reset, restoring 25% of their monthly quota (usage below 25% resets to zero), equal to one week of usage. Your usage bar will reflect this adjustment by end of day PST.
We've also adjusted the plan's parameters and are reducing unnecessary subagent calls and output length, so your quota goes further.
Thank you for your patience while we put this right.
Kimi Yes！！！！
看起来和 opus 5.5有的一拼啊！
Introducing Kimi K3.1 Pro: our most capable 3T-class open-weight model.
🔹 1M-token context, 2.8T total / 104B active params (MoE), Multimodal.
🔹 Full-project coding: games in Unreal, Unity & Godot.
🔹 Excels at parametric 3D modeling in Blender & CAD.
🔹 More reliable at finance work: Accurate modeling with hallucination down by 65%.
🔹 Matching the strongest proprietary models across coding, agentic and knowledge benchmarks.
Kimi K3.1 Pro and K3.1 Pro Highspeed (2–3× faster) are now live on Kimi.ai, Kimi Work, Kimi Code, and the Kimi API.
Open weights by Nov 4, 2026.
🔗 API: platform.kimi.ai
🔗 Tech blog: kimi.ai/blog/kimi-k3-1-pro
对不起 Vaultwarden(Bitwarden)，我又回到 1password 了。。。。。咸鱼上40元4年，，太香了。。。
Today we announce 1Password for Agents platform, building with companies @Muse, SpaceX Super Intelligence Grok @Bot, @AnthropicAI’s @Claudeai, @OpenAI, @TownAI, @Browserbase, @Browser_use, @heydana_ai, Instinct, @usekernel, @Perplexity_ai, @tryramp, @Tomo, and @wajo_ai, with more integrations on the way. 🎉
We've heard from so many of our customers who want to use these new personal AI agents to help them get more done, but want more control over what the agent can access with the same trust and ease of use they get when using 1Password directly.
1Password for Agents gives your agents access without giving up your passwords. When an agent reaches a sign-in form, it requests a credential from your vault. If you approve the request, 1Password directly auto-fills the credential in the destination site so the agent can’t see or take possession of the credentials.
The agent gets the task done, but it doesn’t get your passwords..
You stay in control. 1Password for Agents free and optional for personal and family accounts. Unless you opt-in to an agent connector, agents cannot touch your vault.
➡️Learn more: bit.ly/487da6J
才发现 Zed 团队开发了个 ADE: Delta，目前处于 Public Beta
看起来依旧很简洁，审美在线
主要创新是为消灭传统 PR 而生的 DeltaDB：
它在 Git 底下加了一层 DeltaDB，除了记录文件改动外，还记录了生成这次提交的提示词和对话内容
重点是，它除了可以审查 Agent 对话内容以外，还可以直接还原整个会话，然后继续对话，挺有意思的
delta.dev/
哈哈，好可爱，黄仁勋在 GTC 上和 @pollenrobotics 的可达鸭互动，真好玩，一个400刀，好想要，可惜中国区没得买
Jensen closed his GTC Berlin 2026 keynote with this Hermes Agent demo as the finale.
He introduced it by saying the way to build an agent is to ask an agent to build it for you, so he installed and set up a customized Hermes in one prompt.
Then he used Hermes, running on @nvidia RTX Spark, to create a simulated training environment for the @huggingface Microduck. Hermes planned an obstacle course with Nemotron and had GPT-6 Astra build it using FreeCAD, Omniverse libraries, Blender, Newton, and Isaac Lab. Hermes trained thousands of simulated ducks on that course until the validated policy was ready to run on the real robot in the physical world.
At Nous, we believe open source is a practical tool as much as a philosophical ideal. It gives users the ability to build powerful, complex workflows chaining numerous local+cloud models, devices, and tools themselves instead of waiting for a company to enable them.