🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Interested in reading a GREAT article that should NOT have been written? I can only hope that we make sure that this article will be the first and the last! Stay tuned for a follow-up on #Chemistry, data, and #openscience doi.org/10.1021/acs.jc… Kevin M Jablonka EPFL Chemistry

Interested in carbon capture and MOFs? What about machine learning? Check out our work on the heat capacity of nanoporous materials(🧵👇): chemrxiv.org/engage/chemrxi… with Charithea Charalambous Daniele Ongari Mehrdad Asgari Amir Farmahini, Frank Noe, Susana Garcia, Lev Sarkisov, Berend Smit

What do you do if you don’t have any data and your boss wants to do #machinelearning anyway? Fortunately, Mohamad Moosavi did not change boss and developed a beautiful ML model to predict the heat capacity of MOFs, rdcu.be/cXvAy 1/3

I've seen things you people wouldn't believe: COFs on fire off the shoulder of Orion, I watched doped COFs glitter in the dark near the TannhäuserGate. All those papers will be lost in time, like tears in rain. Time to be terminated, maybe. Have mercy on us Elon Musk. MOF Papers

The most controversial article I have ever written! Kevin M Jablonka shows that making a #MachineLearning model for different problems in #Chemistry with #GPT3 is as easy as a literature search. The scary part; it outperforms all the conventional ML models dx.doi.org/10.26434/chemr… 1/4

With many 🧩 dropping recently, a more complete picture is emerging of LLMs not as a chatbot, but the kernel process of a new Operating System. E.g. today it orchestrates: - Input & Output across modalities (text, audio, vision) - Code interpreter, ability to write & run

Interesting COF paper published in today's Nature issue. Congratulations to Zheng and coauthors!

Excited about our just-out Nature article! 🌟 A standout: a machine learning study where we used net-carbon avoidance cost to identify top-performing materials. Started with 20, #MachineLearning added 135 more, boosting commercialization chances! doi.org/10.1038/s41586…