@LiorOnAI José here—creator of Mathify—big fan of 3blue1brown
I invite you to check out Mathify
I would love to know your thoughts and advice 🙂
https://t.co/FSektvxesT
Introducing the remix feature of https://t.co/e0HRHTrpje!
Over 100 people have tried out Mathify, and now everyone can build up on the public creations of the community by remixing them, similar to the feature of platforms like Instagram and Lovable.
#AI4Science#AI4Math
Our original Twitter account has been compromised, and we are unlikely to get it back.
Please follow this new account and join our new Discord server, https://t.co/S8MtGPB6vw, for updates.
@traversymedia José here—creator of Mathify—big fan of yours since my early days learning web dev, although I haven't completed one of courses in quite a while
But gotta say: You're so back!
I'll be waiting for it 🙂
@birk@polar_sh José here—creator of Mathify—big fan of polar
This is an interesting insight
Do you have ideas on how to make it work on products that have an AI usage bill?
Lifetime access doesnt work well if usage cost grows proportionally
I've been thinking of Pay-As-You-Go $10 packages
Reinforcement learning is the special sauce that enables AI scientists and agents to learn by experimentation and make decisions in complex, uncertain environments. Read our latest @nvidia tech blog cowritten with @EdisonSci and @FutureHouseSF on using RL for scientific agents
@markchen90@paulg One issue though might be reproducibility
If they are using ChatGPT, the product and the model would get updated
It would be nice if versions and configurations could be pinned for scientists
Then the models could be analyzed further to provide insights on how their "thinking"
Introducing the remix feature of https://t.co/e0HRHTrpje!
Over 100 people have tried out Mathify, and now everyone can build up on the public creations of the community by remixing them, similar to the feature of platforms like Instagram and Lovable.
#AI4Science#AI4Math
Nobody’s ready for what this Stanford paper reveals about multi-agent AI.
"Latent Collaboration in Multi-Agent Systems" shows that agents don’t need messages, protocols, or explicit teamwork instructions. They start coordinating inside their own hidden representations a full collaboration layer that exists only in the latent space.
And the behaviors are insane:
• Agents silently hand off tasks based on who’s better
• Roles appear out of nowhere leader, executor, supporter
• Policies encode signals that never show up in actions
• Teams adapt to new environments without retraining
• Collaboration stays stable even when communication is impossible
The wildest detail:
Even when you remove all channels for communication, agents still cooperate. The “teamwork” doesn’t live in messages. It lives in the network.
This flips the entire multi-agent playbook.
We’ve been building coordination mechanisms on top…
while the real coordination is happening underneath.
A new era of emergent team intelligence is unfolding — and it’s happening in the places we weren’t even looking.
Project: github. com/Gen-Verse/LatentMAS
Introducing Mathify
AI-powered math & physics animations — instantly
For the past months I’ve been building Mathify, a tool that turns math and physics ideas into clean, Manim-style animations with a single prompt
No scripts, no setup, no GPU headaches
https://t.co/78kPv37lIZ
New post is live:
"Introducing Mathify — AI-Generated Math Animations"
📄 Read it here: https://t.co/xpndYSsRFm
If you want to follow future updates, subscribe to our blog.
Check out the latest community creations on Mathify! 💡📈
https://t.co/wCUxzg2lXi
It’s a small update but it makes a real difference. Very soon you’ll be able to remix any creation, iterate on it, and help push the animations even further as a community.
#AI4Science#AI4Math