I overlooked Matt's truck driver compressor. It really would drive. It SEES the
road after dataset is digested, and control the truck controls. It'd turn when
see similar cues etc. It'd go to the most common destination, food store.
Though it isn't superior to a text/vision compressor because the visual data
needs to be not just streets lol, and the prediction needs to be diverse
sensory data as well not just motor controls. And a walker bot that just learns
to walk/barricade like OpenAI showed can't solve problems not in front of
themselves, unlike the Thinker types that can ex. GPT-2.
------------------------------------------
Artificial General Intelligence List: AGI
Permalink:
https://agi.topicbox.com/groups/agi/Tc67faac3048278cf-M1bc75700040dc0860ec301b7
Delivery options: https://agi.topicbox.com/groups/agi/subscription
