My dad consistently talks about this show whenever I bring up anime because he used to wake up very early to watch it, and I still kind of forget that it’s a real show that existed.
December 20, 2025 at 8:58 PM
My dad consistently talks about this show whenever I bring up anime because he used to wake up very early to watch it, and I still kind of forget that it’s a real show that existed.
The Houston Museum of Natural Science does have a relatively large number of Fabergé pieces (as well as some others in the style of Fabergé that are equally as impressive), but much of the value there comes from the artistry rather than the gemstones themselves being high value.
October 20, 2025 at 2:37 PM
The Houston Museum of Natural Science does have a relatively large number of Fabergé pieces (as well as some others in the style of Fabergé that are equally as impressive), but much of the value there comes from the artistry rather than the gemstones themselves being high value.
There are absolutely generative AI models being developed for molecular design tasks, and I know because I work in computational chemistry…
Like here’s an early example from 2018 (models have _significantly_ improved since then). It’s not just screening tools anymore.
doi.org/10.1021/acsc...
Like here’s an early example from 2018 (models have _significantly_ improved since then). It’s not just screening tools anymore.
doi.org/10.1021/acsc...
Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules
We report a method to convert discrete representations of molecules to and from a multidimensional continuous representation. This model allows us to generate new molecules for efficient exploration a...
doi.org
October 11, 2025 at 2:33 PM
There are absolutely generative AI models being developed for molecular design tasks, and I know because I work in computational chemistry…
Like here’s an early example from 2018 (models have _significantly_ improved since then). It’s not just screening tools anymore.
doi.org/10.1021/acsc...
Like here’s an early example from 2018 (models have _significantly_ improved since then). It’s not just screening tools anymore.
doi.org/10.1021/acsc...
Very specific models trained for very specific tasks _can_ have useful scientific research applications, but those models are doing things proposing candidate molecules for hard molecular design problems (e.g. drug candidate searches). For the commercial models? I got nothing…
October 11, 2025 at 6:03 AM
Very specific models trained for very specific tasks _can_ have useful scientific research applications, but those models are doing things proposing candidate molecules for hard molecular design problems (e.g. drug candidate searches). For the commercial models? I got nothing…