𝖡.𝗄𝖾𝖾𝗇
5.1K posts
개가 물면 뺄게 아니라 더 밀어넣어야한다.
손을 물렸으면 엄지로 연구개 잡으면서 그대로 들 수 있다. 연구개는 강하게 잡으면 다치니깐 적당히 눌러 잡고.
다리나 팔로 누르면 힘조절이 어려우니 손을 내어주는걸 추천.
Haru-삼촌@lmc8710
아무나 개를 키우면 안되는 이유 주인이 전혀 제지를 못하네...
한국어
𝖡.𝗄𝖾𝖾𝗇 がリツイート
트이타에 중국을 좋아하고 안좋아하는 사람만 있지
건조하게 분석하는 사람은 별로 없다
자동차 한정해서 얘기하자면
한국은 당연한거고
미국도 3, 4년내로 크게 ㅈ되게 생긴 상황이다
중국은 미국을 갈라파고스화 시킬 것이다
한국어
𝖡.𝗄𝖾𝖾𝗇 がリツイート
𝖡.𝗄𝖾𝖾𝗇 がリツイート
这个也太屌了！
这个中国开发者在飞机上用 MacBook 本地跑 Llama 70B，整整 11 小时没有网络，处理了完整的客户项目。
他坐在跨大西洋航班的靠窗位置，设备是 MacBook Pro M4，64GB 内存。机上 WiFi 要价 25 美元，他拒绝了。
没有云端 API，没有连接 Anthropic 或 OpenAI 的服务器，完全没有互联网。
只有一台本地运行的 Llama 3.3 70B（bf16）和他自己写的编排脚本。
模型通过 llama.cpp 运行。生成速度 71 tokens/秒，上下文约 60,000 tokens，内存占用 48.6 GiB / 64 GiB，起飞时电池剩余 3 小时 21 分钟。
起飞前他给编排器写了这样的系统提示：
"你是一个运行在单台 MacBook 上的离线编排器。没有网络。你唯一的资源是 /Users/dev/work 下的本地文件、localhost:8080 的 Llama 70B 推理服务，以及 3 小时 21 分钟的电池预算。处理 /Users/dev/work/queue.jsonl 中的任务队列（每行一个客户任务）。对每个任务：起草 → 运行本地评估 → 保存产物到 /Users/dev/work/done/。每 12 个任务保存一次上下文检查点，以便更换电池后恢复。仅在队列为空或电池低于 5% 时停止。"
所以这个系统完全清楚自己运行在什么资源上。
它知道自己未来 11 小时没有外部连接。它知道自己的内存和电池都是有限的。它知道在飞机降落之前不会有人类介入。
系统跑在一个循环里。从队列取任务，推理，保存产物，写检查点。一个接一个。
当电池低于 5% 时，编排器自动暂停，等待笔记本切换到备用充电宝，然后从最后一个检查点恢复。
这是系统在飞行中的日志：
"saved context checkpoint 8 of 12 (pos_min = 488, pos_max = 50118, size = 62.813 MiB)"
"restored context checkpoint (pos_min = 488, pos_max = 50118)"
"prompt processing progress: n_tokens = 50 / 60818"
"task 37016 done | tps = 71 s tokens text → /Users/dev/work/done/proposal_westside.md"
窗外是云层、蓝天，没有 WiFi。托盘上是一台 MacBook，一个打开的终端，两个屏幕，一个 localhost 推理服务。
这是过去一年里我见过的最漂亮的离线 AI 工作流：
11 小时飞行，WiFi 费用 0 美元，所有客户队列在降落前全部清空。
这个故事的核心不是技术多牛（llama.cpp 跑 70B 现在很常规），而是一个完整的离线自主工作流，编排器理解自己的资源约束，自动管理电池和检查点，没人干预干了 11 小时。
这种"self-aware computing"的感觉确实挺酷的！
x.com/i/status/20499…
Blaze@browomo
This Chinese developer launched Llama 70B locally on a MacBook on a plane and for a full 11 hours without internet ran client projects. He was sitting by the window on a transatlantic flight with a MacBook Pro M4 with 64 GB of memory. WiFi on board cost $25 for the flight. He declined. No cloud API, no connection to Anthropic or OpenAI servers, no internet at all. Just a local Llama 3.3 70B on bf16 and his own orchestrator script. The model runs through llama.cpp. Generation speed, 71 tokens per second. Context around 60,000 tokens. Memory usage, 48.6 GiB out of 64. Battery at takeoff, 3 hours 21 minutes. And he gave the orchestrator this system prompt before takeoff: "You are an offline orchestrator running on a single MacBook. There is no network. The only resources you have are local files in /Users/dev/work, the Llama 70B inference server at localhost:8080, and a battery budget of 3 hours 21 minutes. Process the queue at /Users/dev/work/queue.jsonl (one client task per line). For each task: draft → run local evals → save artefact to /Users/dev/work/done/. Save context checkpoints every 12 tasks so you can resume after a battery swap. Stop only on empty queue or when battery drops below 5%." So the system knows exactly what resources it is running on. It knows it has no connection to the outside world for the next 11 hours. It knows it has finite memory and a finite battery. It knows the human will not intervene until the plane lands. The system runs in 1 loop. Takes a task from the queue, runs it through inference, saves the artifact, writes a checkpoint. Task after task, just like that. And only when the battery drops below 5% does the orchestrator automatically pause, waits for the laptop to switch to the backup power bank, and continues from the last checkpoint. Here is what the system actually writes in his log during the flight: "saved context checkpoint 8 of 12 (pos_min = 488, pos_max = 50118, size = 62.813 MiB)" "restored context checkpoint (pos_min = 488, pos_max = 50118)" "prompt processing progress: n_tokens = 50 / 60 818" "task 37016 done | tps = 71 s tokens text → /Users/dev/work/done/proposal_westside.md" Outside the window, clouds, blue sky, and no WiFi. On the tray, 1 MacBook, an open terminal on 2 screens, and an inference server on localhost. From what I have observed, this is the cleanest offline AI workflow I have seen in the past year: 11 hours of flight, $0 for WiFi, and the entire client queue closed before landing.
中文
𝖡.𝗄𝖾𝖾𝗇 がリツイート
𝖡.𝗄𝖾𝖾𝗇 がリツイート
𝖡.𝗄𝖾𝖾𝗇 がリツイート
𝖡.𝗄𝖾𝖾𝗇 がリツイート
나 아우디 좋아하는데 기아차 느낌이 살짝 있네.
Hwang moon-gyu@Timbretop
아우디 new A6 풀체인지 모델인데 잘 나온 듯. 초도물량 6천대를 주문했다는데 추가 주문한다고.
한국어
𝖡.𝗄𝖾𝖾𝗇 がリツイート
Codex가 이제 며칠 동안 빡센 태스크 붙잡고 있는 게 된다고 함. 찔러보고 안 되면 포기하는 게 아니라 끝까지 물고 늘어지는 에이전트가 나온다는 건데 ㅋㅋㅋ 이게 대중화되면 개발자는 큰 그림만 그려두고 디테일은 AI한테 며칠 맡겨두면 끝임. 결국 실시간 채팅의 시대는 가고, 비동기로 묵직하게 결과 뽑아내는 놈이 이기는 시장이 올 것 같아.
Tibo@thsottiaux
With some small tweaks, Codex can work for days on hard tasks. We will release some changes to make this easier to use for everyone. What’s the hardest task you’ve seen GPT-5.5 succeed at?
한국어