Rui Wang

Research Lead @yutori_ai, building computer-use models. Previously, post-training lead of Llama 3 Multimodal @AIatMeta, computer vision @FAIR.

[Rui Wang @theruiwang]

@ericjang11 Happy to chat! My robots crash in operating systems instead of into walls 😄

[Rui Wang @theruiwang]

@chihyaoma Congrats!

[Rui Wang @theruiwang]

Docs: https://t.co/o00gXT4K0G

[Rui Wang @theruiwang]

n1.5 is now serving production CUA traffic at a FAANG company after extensive evals against models from big labs on both accuracy and efficiency.

If you’re currently using Claude / Gemini / GPT as a web agent, it’s worth trying Navigator n1.5 — it will likely reduce cost, improve latency, and deliver stronger performance.

[Devi Parikh @deviparikh]

We gave some of our partners early access to n1.5 — the most capable computer use model for the web.

It is in production at FAANG scale as we speak, replacing a computer use model from a frontier lab.

If your product can benefit from web automation — extracting structured data from dynamic webpages, filling forms, completing workflows on the web, testing vibe coded web apps — you should try out @yutori_ai's Navigator n1.5!

Save your GPT / Claude / Gemini capacity for something else :)

[Maximillian Piras @MVXMXM]

🖱️ n1.5

[Rui Wang @theruiwang]

It’s a good model. We optimized it for real-world usage, not benchmarks.

Try it: https://t.co/o00gXT4K0G

[Rui Wang @theruiwang]

A conceptually simple web task can become a “long-horizon” task for today’s computer-use models.

If a model can only act through UI primitives, click, type, scroll, everything gets forced into a sequence of low-level operations. Even simple tasks turn into dozens of steps: filling forms field by field, clicking through variants, and executing long sequences of small, incremental interactions.

We introduced a hybrid mode: vision + DOM + code. Pure vision generalizes but is unnecessarily slow; pure DOM + code is fast but can be brittle given the current state of the web. The hybrid combines both, taking the fast, programmatic path when possible, while using vision to verify against what’s actually rendered.

The result: "long-horizon" tasks collapse into shorter ones—less time, less compute, and more reliable outcomes.

[Dhruv Batra @DhruvBatra_]

𝐈𝐧𝐭𝐫𝐨𝐝𝐮𝐜𝐢𝐧𝐠 𝐍𝐚𝐯𝐢𝐠𝐚𝐭𝐨𝐫 𝐧𝟏.𝟓

The most capable computer-use model for the web.

Pareto-domination: accuracy, latency, cost

• SoTA across all benchmarks
• +5-10% over GPT 5.5, Opus 4.7, n1
• +25% over Gemini
• 2x faster, significantly cheaper

Expanded action space
• UI actions (like n1)
+ JavaScript generation & execution

[Rui Wang @theruiwang]

@DhruvBatra_ It’s a good model! We optimized it for real-world usage, not benchmarks.

Try it: https://t.co/o00gXT4K0G

[Rui Wang @theruiwang]

https://t.co/yPw3LCD4xf

[Devi Parikh @deviparikh]

Why 996 when 007 has you covered?

Try Yutori Delegate.

[Crusoe @CrusoeAI]

Stop micromanaging AI. Start delegating. Congrats on the launch, @yutori_ai 🤝

[Rui Wang @theruiwang]

Today we’re launching Delegate!

Let Delegate handle the busywork so you can focus on the outcome and move on with your life.

From coworking → delegating.

Try it: https://t.co/YQ4x8Bvqh2

[Abhishek Das @abhshkdz]

We're excited to launch Delegate. An agent you delegate work to and move on with your life.

[Rui Wang @theruiwang]

RT @DhruvBatra_: Introducing Yutori Delegate.

Why co-work when you can delegate?

[Devi Parikh @deviparikh]

This is what we started Yutori for, and today we're launching it!

Meet Delegate.

Designed for delegation, not chat. It’s proactive, it’s always on, it remembers.

It connects to your apps and learns your context — who you are, how you work and what your priorities are.

It schedules itself forward, it follows up, it follows through.

You don’t need the perfect prompt. Just do a stream of consciousness brain dump of everything on your mind. Delegate it all. And move on. It will break things down. Finish what it can. Come back for input where it needs it.

Try it! https://t.co/T2wH2mgyPf

[Abhishek Das @abhshkdz]

We're excited to launch Delegate. An agent you delegate work to and move on with your life.

[Devi Parikh @deviparikh]

Yutori at this morning's @Nasdaq bell ringing :)

Thank you @notablecap and partners for including us in the Prosumer AI 40 list!

[Abhishek Das @abhshkdz]

We just shipped the biggest update to Scouts since launch (and yes, we know what day it is).

Scouts used to be just for monitoring. Now they act.

Scouts is now a general-purpose task execution engine for the web. Tell it what you need done, and it does it: across any website, behind any login, connected to your apps.

🧵

[Rui Wang @theruiwang]

Today we’re releasing n1, our CUA model for web tasks, now available via API.

- State of the art on browser-use benchmarks
- $0.75 / $3.00 per million input / output tokens
- 2× faster than alternative CUA models

Blog: https://t.co/R9cJIoO7ec

[Devi Parikh @deviparikh]

Introducing n1 — Yutori’s browser-use model.

Available today via our API.

If you’ve been using Claude, Gemini or OpenAI’s computer use models for browser automation — you should switch to Yutori’s n1. It is more accurate, significantly cheaper, and a drop-in replacement.

[Devi Parikh @deviparikh]

It begins!

[Devi Parikh @deviparikh]

Yutori is sponsoring Creators Corner's Agentic Orchestration Hack!

Come build on Yutori's API. Besides access to state-of-the-art web agentic tech, there will also be prizes for the Best Yutori API projects! A large part of the @yutori_ai team will be there through the day — come say Hi :)

January 16th.