News for hackers. Stuff that matters.
Re:Grandmaster-Level Chess Without Search by pertymcpert on Friday October 18, 2024 @03:52AM (#41877220)
Zero doesn't mean zero shot learning. It was coined by Deepmind for AlphaGo Zero where they used zero human input into the training data. It was trained entirely by playing against itself.
Re:Grandmaster-Level Chess Without Search by hilux on Friday October 18, 2024 @05:14AM (#41877629)
And they gave Sir Demis a Nobel Prize!