David Nintang

@odin_free @browomo Real

@davidnintang @browomo building for twitter

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.

@OpenAIDevs Quite simple, but huge!

You can build interactive applications with gpt-realtime-1.5, so users can control app state more naturally with voice. Hi Chappy 👋

Servers for blockchain???

see you tmr :)

@_catwu Being able to view the prompt content of the subagent as well as the work it’s doing is also pretty neat

@_catwu I actually love it! The highlights for me are geeing which sub agents, and tasks are running, and how many of them are complete.

Over the past few weeks, I’ve become a daily user of Claude Code on desktop. It’s the best way to kick off and manage multiple CC sessions across local and cloud in one place. You can also see git status, pin active sessions, and drag and drop layout to view multiple sessions at the same time! Let us know what you think :)

@hthieblot Automations

pitch me your company in 1 word.

Today, we’re launching @autoaicam, a camera that builds personal apps for anything you point it at. How does it work? - Take a photo - Auto picks a Frame, a mini-app built and designed by you or our community - The Frame does something for you: track calories, virtually try on outfits, identify a plant, and much more How many of you have a camera roll full of photos that are really actions or reminders? Auto turns these photos into something useful.

A cheat code to life is being delusional

waitttt, hahahaa😂😂

huh?

Introducing GLM-5.1: The Next Level of Open Source - Top-Tier Performance: #1 in open source and #3 globally across SWE-Bench Pro, Terminal-Bench, and NL2Repo. - Built for Long-Horizon Tasks: Runs autonomously for 8 hours, refining strategies through thousands of iterations. Blog: z.ai/blog/glm-5.1 Weights: huggingface.co/zai-org/GLM-5.1 API: docs.z.ai/guides/llm/glm… Coding Plan: z.ai/subscribe Coming to chat.z.ai in the next few days.

@marceloclaure Short term pain. Long term gain.

One skill I envy most is writing… like GOOD writing

They are probably going to be best friends 5 years from now and laugh about it 😂😂

@eternaltxts Write as often as you can (without AI) either publicly or just for yourself - that makes you think better and keeps you focused. Read as much as you can - that gives you more to think about and make you write better.

@eternaltxts take any particular hobby you have and try to make $100 with it this month. not with the goal to start a business, just to learn what it feels like to try to get a stranger to pay you. it'll rewire your brain