Hacker News Reader

So what happens in the far future when we send autonomous machines equipped with models trained on Earth life and structures to other planets, are they going to have a hard time detecting and measuring things? What happens when the model is tasked with detecting the depth of an object that’s made of triangular glowing scales and the head has three eyes?

View on HN

It would be fairly easy to construct something like this it's never seen before to test it. Go try it. Cut some shapes out of paper or 3d print something weird.

I'd suspect that a good model will infer what it can from universal depth cues (E.g. Bokeh and perspective) when present but not perform as well if they're as not there or as well as it does on familiar objects.

Assembly Theory

Reply on news.ycombinator.com