alt Hacker NewsI am a little worried that this is still a problem after 20 years. Don't they have simulators to test every weird and unexpected road condition offline? And flooded roads aren't exactly an unusual event to begin with.
Replies
They can simulate "driving out of a raging fire" but not a flooded street? This seems like an admission that the fancy "world model simulation" doesn't actually mean much
https://waymo.com/blog/2026/02/the-waymo-world-model-a-new-f...
It can just mean that nobody though about flooded streets, what's way more reasonable than it seems because of the birthday paradox.
But that also means they need a long time to adapt to a new situation. That may be very bad depending on how fine grained a situation is defined, or it may mean nothing and in a few months they'll be back without problems.
It’s been clear for a while to anyone without money riding on this that the relatively “easy” part fooled a lot of people into assuming that the last push to full self driving wouldn’t be radically greater challenge.
The fact that they aren't a usual event is probably exactly the challenge here.
In ATL this happens often enough that it's not a shock when it happens, we have lots of drainage problems here. I agree that I would have assumed Waymo had tested in events like this, but clearly not. So what I can say is running in ATL is a great test case for these events, and also the people who live here don't do a better job than Waymo did. There were dozens of people who ruined their cars yesterday trying to drive through deep water.