OPC’s Post

OPC reposted this

View profile for Eric Vyacheslav, graphic

AI/ML Engineer | Ex-Google | Ex-MIT

H Company might've just created the best AI agent yet. After raising $200M, they just introduced an agent that can execute any task from a prompt. Their "Runner H" can basically turn instructions into action with human-like precision. Features: ▸ Navigates web interfaces with pixel-level precision. ▸ Interprets pixels and text to understand screens and elements. ▸ Automates workflows for web testing, onboarding, and e-commerce. ▸ Adapts automatically to UI changes. ▸ Achieves a 67% success rate on WebVoyager, outperforming competitors. Architecture: ▸ Powered by a 2B-paramezer LLM for function calling and coding. ▸ Includes a 3B-parameter VLM for understanding graphical and text elements. You can signup for the private beta here: https://lnkd.in/gdrK6u6A

Lindsay Richman

Founder, Innerverse AI | McKinsey Alum | Google for Startups | VentureBeat Top Woman in AI

1w

How is this different from function calling? Also, someone else posted this with basically same wording yesterday so this makes me question the authenticity and incentives here...

Cedar Milazzo

Inspiring teams, building amazing cultures, and bringing the future to life!

1w

67% May be better than the competition, but in reality it’s not that useful. Do you really want a tool that fails 1/3 of the time?

Charles Demontigny

⚡️Try Capture 🤖 text it at 514.700.6667 📞

1w

The marketing team is usually better than the engineering one. How many videos like this one have we seen in the last year?

Navaneeth Sankar K P

UX + Data Science = Remarkable Products • MIT-ID, Pune | IIT-Madras B.S ongoing | FDE'24 | ICoRD'25

1w

Thoughts on how this will impact web design? Sanjog Bora Vikhyat Kaushik

Ion Moșnoi

8+y in AI / ML | genAI MVP in weeks | fix AI agents | RAG retrieval | continuous chatbot learning | enterprise LLM | NLP | Python | Langchain | GPT4 | AI ChatBot | B2B Contractor | Freelancer | Consultant

1w

QA testers are finished :D

Yasin Ehsan (Hiring) 🚀

CEO of Headstarter | Building Top 1% Software Engineers | 10x hackathon winner: Overall first at HackCornell, HackNYU, IBM Call for Code, Estée Lauder, Jp Morgan Code for Good, Capital One etc

1w

is this legit? how do we know this isn't just a llama wrapper or some fine tuning on selenium using langchain

Sivaram Sathiamoorthi

L6 TechLead | Data Eng | 'Passionate about solving problem no one asked to solve'

1w

F**k there goes my billion dollar idea 🥲

Eric Vyacheslav This is groundbreaking—AI agents are getting closer to true task automation! For those curious about the implications of advancements like this, we recently had Advitya, a Machine Learning Engineer 2 at Microsoft specializing in Responsible AI, on my YouTube channel Ready Set Do. He shared insights on navigating the challenges of AI development, ensuring responsible deployment, and the future of human-AI collaboration. Definitely worth checking out for anyone passionate about AI! https://youtu.be/OJzpyENIomE

Like
Reply
Victory Adugbo

Hacking Growth for AI, Web3, and FinTech Companies || Blockchain Instructor at CCHUB || Building Smarter Futures for CohorteAI || Turning AI Chaos into Business Success Stories ||

1w

Pixel-level precision for navigating web interfaces is a game-changer for tasks like e-commerce automation and web testing. It’s fascinating how 'Runner H' combines visual and textual understanding for adaptability. How does the system handle highly dynamic or non-standard UIs—are there any constraints or failure modes you’ve identified?

Like
Reply
See more comments

To view or add a comment, sign in

Explore topics