kat(@katclone):Frustrating part of AI models for bio is lack of clarity in what types of data we should be collecting and the sampling rate that provides biological significance. If you look at autonomous driving, progress in that field wasn’t just due to algorithms. Companies had a lot of continuous training data. Imagine training a self driving car with some snapshots from intersections. This is close to the types of data we currently have in biology (sparse snapshots and yet ppl are trying to dynamic systems). Need more/different types of data (more tech?tools?), better sampling rate in many cases (including more informed ways of modeling it).

2026.06.09 20:08

Frustrating part of AI models for bio is lack of clarity in what types of data we should be collecting and the sampling rate that provides biological significance. If you look at autonomous driving, progress in that field wasn’t just due to algorithms. Companies had a lot of continuous training data. Imagine training a self driving car with some snapshots from intersections. This is close to the types of data we currently have in biology (sparse snapshots and yet ppl are trying to dynamic systems). Need more/different types of data (more tech?tools?), better sampling rate in many cases (including more informed ways of modeling it).

显示更多