Introducing Ads Agent!
Everyone sells AI copy. We sell growth.
Ads Agent automates the entire Google Ads pipeline:
Input: Your PRD or Code.
Output: Live, optimized campaigns (Keywords, GA4, Multi-lang).
If manual work is the only thing standing between your product and your market, you just found the solution.
Introducing Atoms: the first AI team that builds real businesses.
From research to build, launch, and scale, all autonomous.
Don’t Vibe Code. Vibe Business.
→ https://t.co/g0L4NRU7xE
Introducing Atoms: the first AI team that builds real businesses.
From research to build, launch, and scale, all autonomous.
Don’t Vibe Code. Vibe Business.
→ https://t.co/g0L4NRU7xE
🚀Gemini 3 is now live on MGX
Available at:
→ https://t.co/cmVlLOkepB
→ Model Settings
→ Advanced Coding (Gemini 3.0 Pro)
Experience stunning dynamic, interactive output
Now boosting your no-deploy MGX projects with even higher efficiency.
Here are a few examples🫡
A critical blind spot in AI search agents has been exposed
New research reveals that while AI search performance has improved 7-fold, interaction capabilities have stagnated. Agents are overconfident, failing to clarify ambiguous queries, even when they could.
Very proud to be the corresponding author driving ReCode forward.
It’s one of our 20+ key ideas, which is simple, elegant, and with infinite potential.
Is ReAct the final for LLM Agents? 🤔
Not anymore. ReAct is stuck step-by-step. Planning agents separate plans from actions.
Introducing ReCode: agents control their decision granularity, like humans do.
20.9% better, 78.9% cheaper, 3.7× data efficient. The ReAct era is over.
1/5
@Hesamation Thank you! This work is based on the mapping of the human brain and AI that I drew in 2023, and now we have completed it. At first we only wanted to write 70 pages, but the authors were so enthusiastic that they wrote 264 pages. Follow us and there will be updates soon!
LOL Thanks @Hesamation. We wanted to write 70 pages at first, but the authors were so enthusiastic that they wrote 264 pages. The corresponding repo: https://t.co/yVcH9a9ybK
the best researchers from Meta, Yale, Stanford, Google DeepMind, and Microsoft laid out all we know about Agents in a 264-page paper [book],
here are some of their key findings:
Bang led this effort brilliantly, coordinating over 40 people across 20 teams. While our initial goal was a modest 70-page document with 500 citations, the team's enthusiasm propelled the project to an impressive 264 pages with 1,416 citations. You all did exceptional work!
🧠264 pages and 1416 references chart the future of Foundation Agents.
Our latest survey dives deep into agents—covering brain-inspired cognition, self-evolution, multi-agents, and AI safety.
Discover the #1 Paper of the Day on Hugging Face👇:
https://t.co/CvtqGKyCYb
1/3
🧠264 pages and 1416 references chart the future of Foundation Agents.
Our latest survey dives deep into agents—covering brain-inspired cognition, self-evolution, multi-agents, and AI safety.
Discover the #1 Paper of the Day on Hugging Face👇:
https://t.co/CvtqGKyCYb
1/3