Kevin M Jablonka Profile picture
Trying to teach computers about chemistry and materials @jablonkagroup @UniJena. You can use https://t.co/HXvlhpq56i to provide feedback.
Mar 15, 2023 7 tweets 3 min read
Testing now some matbench examples. First up, the `is_metal` task. Again, few (=50) shot setting. It doesn't want to predict.

Let's try another one.
Mar 15, 2023 9 tweets 3 min read
One more MOF case study (that also spoilers some work I'm currently working on).

How do I synthesize a MOF? A reasonable, but again general, starting point.

Can it be more specific?
Mar 15, 2023 18 tweets 7 min read
But I am also a digital reticular chemist. Can #GPT4 help me with #MOFs? Asking a very broad and open question about carbon capture. I don't think ZIF-8 is the best choice, but it knows some basic KPIs and MOFs. Does it know really recent research (science.org/doi/10.1126/sc…)?
Mar 15, 2023 20 tweets 8 min read
One of my favorite examples in our preprint (chemrxiv.org/engage/chemrxi…) with @SmitBerend and @pschwllr and @aortegaguerrerowas about photoswitches curated by @Ryan__Rhys.

I now asked #GPT-4 a few questions about it. 1. Few-shot prediction of transition wavelength based on a few examples. We give 50 randomly sampled examples and a prompt like

What is the transition wavelength of CN1C(/N=N/C2=CC=CC=C2)=C(C)C=C1C?
Examples:
---------
• CC1=C(C(C)=NN1)/N=N/C2=CC(OC)=CC=C2: 330.0 nm
...