[florbnit]

Closed loop optimization is already a thing, and you don’t even need AI for it, just good old bayesian optimization is enough.

[photon_mz]

Bayesian doesn't have 'world model' intuition for next experiments to run. Think, human scientists are very 'sample-efficient' at deciding which experiment (i.e. sample) to run, in ways good-ol opt isn't but LLMs could be.

thoughts?

[florbnit]

I feel like you missed the context of my comment. Someone suggested AI would do experiments, someone responded with “lmfao” as a dismissal. I answered that we already have computers running experimental series even without AI. I’m not dismissing AI I’m saying that we are already in a post computer run experimentation world. People not in an industry using that would obviously not know.

[TechDebtDevin]

AI is just good old bayesian :|