News for hackers. Stuff that matters.
Re:OpenAI Five Benchmark: Results by ionforce on Monday August 06, 2018 @07:05PM (#17702543)
If we had the compute luxury, I would love to see more AIs trained with faults like a longer reaction time or deficiencies to make them more human.

But yes, very exciting next stages when there are item builds, more heroes, and standard couriering.

There are no comments on this comment yet.