I think SIAI is focusing on clean AI because most academic research is on messy AI. If you look at the margins, one more unit of research on clean AI is probably more beneficial than one more unit of research on messy AI.
Oh and there’s the selection effect of LW posters replying in an AI thread.
I think SIAI is focusing on clean AI because most academic research is on messy AI. If you look at the margins, one more unit of research on clean AI is probably more beneficial than one more unit of research on messy AI.
Oh and there’s the selection effect of LW posters replying in an AI thread.
There are very few people working on making messy AI Friendly, though. Most of it is charging forward recklessly.