🎉【Gate Singapore Flagship Event · Square Fun Quiz Challenge Day 1】
#TOKEN2049# is just around the corner, and Gate is bringing the heat to Singapore!
Token of Love Music Festival, Gate x Oracle Red Bull Racing Reception, and the F1 Race Viewing are all set to roll out!
Join Square Fun Quiz Challenge now, test how much you know about the events and share $100 BTC in rewards!
To join: Comment your answers (format: 1B 2A 3B 4C)
🎁 Rewards: 3 lucky winners each day → $10 BTC each
👑 Bonus: Answer all questions correctly for 3 days → Extra $10 BTC for Super Quiz King!
📖 Day 1 · Quiz (Single Choic
AI has been taught to comply with the laws of physics in chemistry.
Scientists from MIT have developed an artificial intelligence model called FlowER. It predicts the outcomes of chemical reactions with high accuracy while adhering to the fundamental law of conservation of mass.
According to the authors of the study, previous attempts to use LLM for these tasks had limited success. AI often ignored physical laws and could "create" new atoms or "remove" existing ones during the computation process.
According to him, unlike ChatGPT, their model does not just look at a set of inputs and outputs, but tracks all stages of the transformation of substances.
To solve the problem, the team used a method proposed back in the 1970s — the matrix of connections and electrons. This approach allows the program to track every charged particle in the reaction, ensuring that no atom is created or lost.
The FlowER model was trained on the database of the US Patent Office, which contains over a million chemical reactions. According to the developers, the system already demonstrates equal or higher accuracy compared to existing analogs.
Professor Connor Coley noted that the result of the work only proves the concept for now. The model does not yet cover some reactions with metals and catalysts, but the team is already working on it.
The project is fully open. The code, models, and datasets are published on GitHub. The developers believe that FlowER is already a useful tool for assessing reactions.
In the future, the model may find applications in pharmaceuticals, the search for new materials, and electrochemical systems.
Recall that in 2026, the Chinese technology company Kaiwa Technology from Guangzhou plans to introduce a humanoid robot with an artificial womb in the abdominal area.