teze retweeted
Antik dönemden kalma güzel bir söz var: “Her seferinde intikam almana gerek yok. Çürük meyve, sen dalı sallamasan da düşer.” Zaman işini bilir, sen karışma. Elin kirlenir, meyve yine düşer. Sen kendi bahçene bak.
Replying to @Suercha007
我觉得 很多人是没搞懂PPT的作用,PPT不是炫技,只是辅助表达,是语言的延伸,而很多人却恰恰反过来了。
见过很多西方的教授讲课 ppt都是很素的
teze retweeted
今天我在本地深度逆向Google Antigravity核心二进制包(客户端版本2.27.0)后发现了很多新东西。
大家都以为 Antigravity 只是Google编程Harness,但逆向其 156MB 的核心后端 language_server 后,发现其底层架构埋藏了大量尚未公开的技术路线:
1. 关于新模型的传闻事实
针对近期 X 社区传闻的 Gemini Carbon 和 Gemini 4 Flash,在当前的二进制中目前只看到了 Gemini 4 Argon(细分为 High / Medium / Low 三档),尚未发现 Carbon 和 4-Flash 的相关独立代号。
2. 开放模型架构支持(BYOM / BYOK)
Antigravity 正在推进开放模型接入,代码中直接定义了:
MODEL_CUSTOM_VLLM:支持接入本地私有化部署的开源模型(vLLM 框架)
MODEL_CUSTOM_OPEN_ROUTER:支持第三方模型聚合路由
Claude 系列的自带 API Key(BYOK)接入协议
3. Project Jarvis:Google 的 Computer Use 浏览器接管代理实锤
代码中发现了专门的模型路由 gemini-v4s-jarvis-sc 与 MODEL_GOOGLE_JARVIS_PROXY,它作为一个专用的Browser Subagent协同运行:
提供 Step_ClickBrowserPixel(屏幕像素级点击)底层动作
完整支持模拟鼠标移动和拖拽、键盘敲击、DOM 解析与页面滚动
主 Agent 写代码的同时,可分流派出 Jarvis 代理接管浏览器进行自动化测试与网页交互。
4. 一批 Google 内部研发代号
OrionFire(与 Jarvis 深度绑定)
CosmicForge
RiftRunner(配有独立的 Thinking 模式)
InfinityBloom / InfinityJet
从这些底层协议看,Antigravity 的终极目标并非单一口径的代码补全器,而是一个可调度本地私有模型、跨模型协同,并集成全自动浏览器操作代理的自主智能体工作台。
teze retweeted
Some magical progress towards "magic state" in quantum!
Our @GoogleQuantumAI team has demonstrated "magic state cultivation" on physical hardware for the first time. The result is a 40x error reduction on our Willow processor vs. previous methods, achieving a state-of-the-art 99.99% logical fidelity.
It's another step towards useful, error-corrected quantum computers to help solve the hardest problems. The result is published in Science today, watch the video below to see how it works
teze retweeted
Habitat is OpenAI's online storage platform that powers everything from ChatGPT to Codex.
It has grown over 10x year over year. Before the Rust rewrite, its Python service handled more than 20 million requests per second at peak.
teze retweeted
Meta's chief ai officer @alexandr_wang :
"Internally at Meta, we have seen cases where, if you develop the right agentic loop and have the right evaluation system and metric for the agents to optimize, a swarm of agents can accomplish more than a team of 100 engineers. They can do it very handily, actually, very easily."
Alexandr Wang was talking to CEO of Y Combinator
@garrytan at Y Combinator Startup School 2026
----
full video link in comment



























