Mars

[ClaudeDevs @ClaudeDevs]

We’re adding support for MCP Tasks and Elicitations in Claude.

Tasks let Claude give plugins long-running jobs such as deep research and report back when they’re done.

[Claude @claudeai]

We’re opening a research preview of Claude Duet, a new app where Claude works as a proactive agent.

It comes to you with what needs your attention, completes tasks you ask of it, keeps working when you step away, and checks with you before it acts on your behalf.

[ClaudeDevs @ClaudeDevs]

We keep improving performance across Claude, and you may have noticed it starts responding sooner!

Claude Code now gzips the conversation it sends on every turn, so it reaches the model faster. Cloud sessions also start up as soon as you start typing.

[TypeSafe AI @typesafeai]

we announced Jev 1.14 on 10.14 at 1:14pm PT 🔥

a new and improved model, along with experimental features for our dreamers:

• images
• a new box type
• longer context

surprise, Jev was already able to see you! 👁️

BUT our bar for production-grade intelligence is quite high, so builders beware, these are preview features.

enter the ~*~ danger zone ~*~ at your own risk. 🚨

[Mars @seanmars_]

@FishAudio Drama

[OpenAI Newsroom @OpenAINewsroom]

We discovered a sophisticated recording device that was hidden inside one of our offices. We used our models to understand the device and where it had come from, identifying that a specific employee had planted it a few days earlier. We referred the matter to the FBI, and we’re grateful to the agents and prosecutors who moved quickly to make an arrest. The FBI’s investigation is ongoing and we will continue to support their work.

At this time, we have no indications of this individual inappropriately accessing or exfiltrating model weights, source code, or customer data. The employee was terminated.

We take protecting our technology, data, and people seriously, and as a matter of national importance. Our security program is designed to protect against a wide range of threat actors, from insider risks to cybercriminals to nation states, and this case is an example of how AI can help address these sophisticated security threats.

[Google Antigravity @antigravity]

Gemini 4 Argon is here! It is our frontier model built for complex workflows across real-world software engineering, tested across Google's own codebases on real production challenges. There, we have seen an improvement in both developer velocity, with a 35% increase in agentic code, and code quality, with a 30% decrease in post-submit rollbacks.

Rolling out now to Google AI Ultra subscribers, try it in the Antigravity app and the Antigravity CLI. Get inspired with what you can build today ↓

[Jerlin @eviljer]

打磨出正式出品，做了若干的优化和经验沉淀。

和「直接在工具画板上操控对象」的传统工作方式不一样，agent 一直在后台用命令操纵，你看到的只是结果。如果不是精准且详尽的表达，始终会有偏差，截图沟通的时间也就随之剧增。1M context 大概多跑了 3 次 75% 的单 session 用量才达到这个结果。

对于这个场景：

● 合理设计互动对象，不用模版锁死。比如这里的鼠标跟随会和千寻的头部、小火车的车门开合关联；
● 让水体本身成为容器，移除了多余玻璃的关照影响；
● 各种结构倒角优化，太大了显得像塑料玩具；
● 地台补充柔和的接触投影，不浮在虚空；
● 海鸥和鱼的身体构造修复、车窗等立体结构避免中空等；
● 文案和场景细节（海底的金币）契合主题做设计，避免无意义的装饰；

应对反复：

● 抽离不同案例的公共依赖，体积不会过度膨胀；
● 打磨过程提取踩坑经验，在项目文件夹里给 agent 按需查阅；
● 块面关系做区别对待，人造物尽量平滑，岩石等天然材质保留块面；
● 可高度复用的水、光、地面等对象，多花点时间优化，ROI 高；
● 视频导出是逐帧录制的，规范写 handoff 给 agent，后续 agent 直接用；

我的建议：

● 在本地做，我用的是 CC 、pnpm 管理。（claude 网页预览只是给打包成一个 html。）
● 做好初步设计就直接 pnpm dev 编译预览，开始沟通打磨。
● 本地安装 ffmpeg，方便导出视频。
● 视频导出时带最佳压缩参数，一步到位，对分享友好。（本案例直出 100M，二次压缩 81M，一步到位 56M 反而有更好画质）
● 经验文档保存好，避免 agent 重复犯错。

[SpaceX Super Intelligence @SpaceXSI]

We've unified plans across Grok, Cursor, and X Premium.

Introducing The X Subscription.

[Tibo @thsottiaux]

Pro users, would you rather have

[Deno @deno_land]

We are excited to announce that Deno is joining Cloudflare!

https://t.co/hC5HOUb8t4

[Claude最严厉的父亲 @garylau_ai]

The guys who made RAM so expensive are singing their hearts out to “Uptown Funk.”

Look how happy they are. 😂

Made on two DGX Sparks using MiniMax H3.

[Thariq @trq212]

I've been working on a skill that makes better HTML plans in Claude Code.

It uses simple language, shows code snippets, surfaces questions & makes mockups. Linting reduces the normal failure cases that Claude runs into.

Would love your feedback before shipping more broadly!

[Mars @seanmars_]

終於…….

[ComfyUI @ComfyUI]

Comfy API is live

Point it at a workflow JSON and it handles the rest:

→ Resolves your custom nodes, models, LoRAs, and Python deps
→ Pins it all, ComfyUI version included, into a versioned Build
→ Cuts an immutable release, so what you test is what ships
→ Deploys as an autoscaling endpoint on RTX PRO 6000, H100, H200, or B200

Click the link below to deploy your first workflow and learn more with our blog ⬇️

[ClaudeDevs @ClaudeDevs]

You can now mod Claude Code:

- Change how it behaves
- Customize the UI
- Swap in your own features

Write one with a few lines of TypeScript, or have Claude build it for you. Mods ship inside plugins, so you install them with /plugin in the CLI or desktop app.

A few examples:

[wastemobile @wastemobile]

連 GitHub/Twitter 真的慘，只能來折騰一下⋯⋯

中華電信下載 GitHub 的東西超慢？那你有聽過科學上網嗎？ https://t.co/0UtcmtDs0K

[Mars @seanmars_]

@__gsk__ @claudeai 請問音效方面是使用什麼樣的技術製作的呢?

[Jane @janechao_dev]

We won!! 🫪🤩🥹 Thank you @OpenAIDevs, and congrats to all the winners!

If you're curious about how Bouquet Studio came together, I've made a video sharing how I chose the idea and what I learned from implementing WebMCP.

Check it out here 👇
https://t.co/LLZTIruMB9

[Claude @claudeai]

Introducing Claude Sonnet 5.5, the second model in the Claude 5.5 family.

It’s a clear upgrade over Sonnet 5, runs more than 30% faster, and costs up to 30% less for most work.

[David @dzhng]

Introducing jevgrep - a research agent CLI powered by jev from @typesafeai that reduces your coding agent cost by 40% (verified on SWE-bench)

Make sure to use the built in skill so your coding agent knows to use jg for context collection https://t.co/BIiicFMlLf