Jordan Stone

Building @askArbiterAI || iOS Dev || WashU’22

[Jordan Stone @JStone2299]

I’ve spent the past few months building Arbiter, a local AI chat app that runs entirely on your device.

The goal: powerful AI without compromising on privacy or environmental impact.

Excited to finally share it with everyone.

[Arbiter - Local AI @askArbiterAI]

Meet Arbiter — a private AI chat app that runs entirely on your device.

Chat, summarize, research, and learn with powerful on-device models like Gemma, DeepSeek, Apple’s Foundation Model, and more.

Available now on iPhone.

https://t.co/SOwjWPrEYY

[Arbiter - Local AI @askArbiterAI]

Every cloud prompt relies on a data center. Every Arbiter prompt runs on your phone. Local LLMs mean no servers and no cloud, just AI that's private, offline, and lighter on the planet.
Download Arbiter today → https://t.co/1YIwj0nfwq

[Arbiter - Local AI @askArbiterAI]

Arbiter for Mac is now available!

Run bigger, faster local AI models on your Mac, optimized for Apple Silicon with MLX.

Download today: https://t.co/1YIwj0mHGS

[Arbiter - Local AI @askArbiterAI]

When you’re traveling internationally, there are plenty of moments where you end up with poor cell service, no Wi-Fi, or no signal at all, especially in more remote areas.

That is exactly when being able to communicate matters most.

Arbiter’s Language Translator mode works offline, giving you a pocket translator without needing a reliable connection.

Ask for phrases, learn vocabulary, and get help communicating wherever you are.

[Arbiter - Local AI @askArbiterAI]

Coming in the next Arbiter release, you can connect to an LLM server on your iPhone.

Run larger models on your computer with LM Studio or Ollama, then chat with them from your iPhone over your local network.

More power than your phone can handle on-device, without relying on cloud inference.

[Arbiter - Local AI @askArbiterAI]

Arbiter supports real-time web search for local AI.

When search is enabled, Arbiter sends a generic query through SearXNG, pulls in relevant results, and gives that context to your local model.

No accounts. No tracking. No search history tied to you.

Local-first by default. Web search only when you turn it on.

[Georgi Gerganov @ggerganov]

llama.cpp now has an official website: https://t.co/vztdUpdBWL

Our goal is to make local AI accessible to everyone, and improving the user experience is a big part of that. On the new landing page you’ll find a single-line cross-platform installer. The installation provides a single unified `llama` entrypoint which you can use to run/serve models and interface with 3rd-party agentic applications.

While oriented towards simplified user experience, the new `llama` application also provides all the advanced functionality of the existing llama.cpp tooling with which experienced users are already familiar. Also note that all GGUF models that you might have already downloaded with llama.cpp in the past will be automatically available to use without downloading again (they are stored in the common HF cache on your machine).

We have many improvements in the pipeline both at the UX and at the engine level and we plan to iteratively ship new things over the coming months. One of the main focuses will be seamless integration with local-friendly 3rd-party agents (such as Pi). In the meantime, we’ll continue to listen for feedback from the community and adjust accordingly, so keep letting us know what you think and need.

[Arbiter - Local AI @askArbiterAI]

We built Arbiter because we wanted an AI that was private by default, not by policy.

Here's something most people don't think about: every message you send to a cloud AI travels to a data center, gets processed on someone else's server, and sits in a database you have no control over.

We didn't want that. So we built something different.

Arbiter runs entirely on your iPhone. It supports powerful open source models like Gemma, Mistral, and Phi all running locally, all offline, all private. No subscription. No cloud. No compromise.

If you've ever felt uneasy about what happens to your AI conversations, Arbiter was built for you.

No servers. No data collection. Just AI that lives on your phone.

Download Free 👇 https://t.co/h1eDw1z37H

[Arbiter - Local AI @askArbiterAI]

What if your AI assistant never needed the internet?

That's Arbiter, fully offline and fully private AI chat on your phone.

Feedback appreciated 👇
https://t.co/1YIwj0mHGS

[Google Gemma @googlegemma]

We are entering a new era of on-device automation. ✨

Watch Gemma 4 E4B navigate and drive an iOS simulator directly using Argent. Local models can handle complex interactions and software navigation autonomously.

[Adrien Grondin @adrgrondin]

Subagents running locally and simultaneously on MacBook Pro M5 with Codex CLI + @lmstudio to review code and find bugs using Qwen 3.6

Powered by the updated MLX engine with batching in beta in the app

The batching speed boost is noticeable

[Arbiter - Local AI @askArbiterAI]

Cloud AI gets expensive fast when usage scales with tokens. Arbiter runs local LLMs on your phone, cutting out the recurring cloud bill for everyday use.
Try Arbiter today!
https://t.co/1YIwj0mHGS

[Arbiter - Local AI @askArbiterAI]

Cool you don't care about AI privacy. What about your electric bill going up to power data centers?

Don't live near a data center? What about rising AI token cost once the bubble pops?

Don't care cause you're rich? What about irreversible environmental harm?

[Jordan Stone @JStone2299]

An AI interface for budgeting is undeniably useful, but it raises real privacy questions about giving OpenAI or any major AI company access to your personal financial data. This is where local AI solutions stand to gain significant market share.

[ChatGPT @ChatGPTapp]

A preview for Pro users: a new personal finance experience in ChatGPT.

Pro users in the U.S. can securely connect financial accounts, see where their money is going, and ask questions based on the information they choose to connect.

Your full financial picture, now in ChatGPT.

[Arbiter - Local AI @askArbiterAI]

There's a growing fight against the rapid construction of AI data centers nationwide. If a task can run on-device, it shouldn't need a data center. Arbiter runs Local LLMs from your phone, cutting unnecessary cloud inference.

Download today → https://t.co/1YIwj0mHGS

[Jordan Stone @JStone2299]

Billionaire oligarchs do not care if you lose everything.

We cannot keep building AI systems that force communities to give up power so data centers can scale endlessly.

As demand for AI grows, focusing on efficient local models will stop being optional and become a necessity.

[More Perfect Union @MorePerfectUS]

Nearly 50,000 people in the Lake Tahoe area have been told that their utility will stop providing power to them, because it's redirecting that power to data centers.

NV Energy, the Nevada utility that has supplied most of Lake Tahoe’s electricity for decades, says that next year it will stop servicing homes in the area, and instead direct that electricity to the growing demand from Nevada data centers.

Northern Nevada is one of the fastest-growing data-center corridors in the country.

https://t.co/nTGJAMbwAP

[Jordan Stone @JStone2299]

@itss_miniii Building @askArbiterAI - a private AI chat app that runs models locally on your iPhone.

[Arbiter - Local AI @askArbiterAI]

Gemma 4 is now available on Arbiter, bringing Google’s latest open models with improved reasoning and image understanding.

Download Arbiter to start using it today! https://t.co/1YIwj0nfwq

[Boring_Business @BoringBiz_]

CFOs realizing that their AI token budget is going to be higher than the salaries of the people they laid off

[Arbiter - Local AI @askArbiterAI]

Arbiter just leveled up! Live Search is here, bringing real-time web results with zero data compromise. Get all the power of up-to-date information while keeping your conversations completely private! 🔍

[Xtine Fang @XtineFang]

"Education is overrated. Go to trade school instead"

-Phillips Andover '14
-Harvard '18
-Yale Law '21