HackerTube 中文?

George Hotz: Hacking the Simulation & Learning to Drive with Neural Nets | Lex Fridman Podcast #132

Lex FridmanYouTube ↗

Further reading 1

A driver took over. What should a driving system learn? →One intersection, a takeover log and a software update. Accounts from openpilot, Tesla and Waymo help separate clues to a failure, examples worth training on and old scenarios that can test a fix.This video helps answer · What does a single takeover label?

Caption notes

Hotz sketches a model-update loop around driver takeovers. The interview distinguishes ordinary manual driving from intervention moments that still need interpretation before they can identify a failure.

Public machine transcript (may contain transcription errors) ↗
Original passages · 2
user disengages, we train on that
George Hotz: Hacking the Simulation & Learning to Drive with Neural Nets | Lex Fridman Podcast #132 · ▶ 61:55–62:00
with some labeling could indicate the failure of the system
George Hotz: Hacking the Simulation & Learning to Drive with Neural Nets | Lex Fridman Podcast #132 · ▶ 65:42–65:47

Hacker News comments

View original on HN ↗