Radar 🧵
1/ Removal of radar from the AP sensor suit seems to be causing distress. The example I see thrown around the most is "what about Inclement weather such as fog?" Its true a radar return can see through fog, however that's only a very small piece of the puzzle. 2/ This intuition presumably comes from the fact as a human driver, I would feel far more comfortable with a HUD that displays the distance and relative speeds to any moving objects in my path.

So why wouldn't a computer get additive value out of this information also?

A follow up 🧵 on Tesla's FSD "rewrite" to explore the Bird's Eye View Networks.

"There are still a few of neural nets that need to be upgraded to video training & inference. And really, as we transition to each net to video, the performance become exceptional." - Elon Musk We can gather from this statement, not all networks are running the BEV mode "rewrite" even for #FSDBeta users. But why is a BEV so much more "performant" compared to a single camera? Let's see what @karpathy has to say about this video:

What is the lauded FSD rewrite @elonmusk is referring to? @karpathy already detailed exactly what it is in Feb 2020 (). Let's discuss... The vector space @elonmusk mentions is a Software 2.0 code rewrite of the occupancy tracker which is now engulfed into a "Bird's Eye View" Neural Net which merges all cameras and projects features into top down view. In @karpathy's own words: "This makes a huge difference".