News for hackers. Stuff that matters.
Re:Andrej Karpathy talks about how Tesla's NNs are structure... by soulslicer0 on Sunday November 10, 2019 @12:13AM (#21496505)
lol i just did the interview and failed. had to find shortest path between tesla chargers. all in C++. completed it but failed
Re:Andrej Karpathy talks about how Tesla's NNs are structure... by lsh on Sunday November 10, 2019 @12:57AM (#21496644)
you were supposed to bore a tunnel directly between the two points
Re:Andrej Karpathy talks about how Tesla's NNs are structure... by mkagenius on Sunday November 10, 2019 @01:07AM (#21496674)
jeez, trick question
Re:Andrej Karpathy talks about how Tesla's NNs are structure... by karpathy on Sunday November 10, 2019 @01:13AM (#21496694)
Very likely not for the positions above! (they all focus on Python)
Re:Andrej Karpathy talks about how Tesla's NNs are structure... by boulos on Sunday November 10, 2019 @01:47AM (#21496777)
Slightly off-topic (but related to the side thread where people didn’t realize you went to Tesla): your HN about still says you’re at OpenAI :).
Re:Andrej Karpathy talks about how Tesla's NNs are structure... by karpathy on Sunday November 10, 2019 @01:50AM (#21496788)
oops, thank you, fixed :)
Re:Andrej Karpathy talks about how Tesla's NNs are structure... by boulos on Sunday November 10, 2019 @02:00AM (#21496822)
As long as you’re here, I’d love to get an updated PyTorch vs TF from you in the sibling thread as payment :).
Re:Andrej Karpathy talks about how Tesla's NNs are structure... by bitL on Sunday November 10, 2019 @01:26AM (#21496727)
IoU
Re:Andrej Karpathy talks about how Tesla's NNs are structure... by ars on Sunday November 10, 2019 @02:03AM (#21496831)
How does that work? Where you given the algorithm to use? Or was it really a data science question, rather than a programming question?
Re:Andrej Karpathy talks about how Tesla's NNs are structure... by meheleventyone on Sunday November 10, 2019 @03:00AM (#21496985)
Without more details it sounds like an algorithm problem you'd be expected to solve from prior knowledge. Stuff like a breadth first search from the start point, up through various path finding algorithms to applying heuristics (I believe route finding on roads exploits the road topology).
Re:Andrej Karpathy talks about how Tesla's NNs are structure... by f00_ on Sunday November 10, 2019 @01:52AM (#21496791)
Could you have just used dijkstra or breadth first search?