News for hackers. Stuff that matters.
Re:Positions chess engines don't understand by hatsunearu on Monday May 17, 2021 @09:39PM (#27190422)
Is there a video of this?
Re:Positions chess engines don't understand by adotbacon on Monday May 17, 2021 @11:35PM (#27191004)
Yes, here's an example of the "cheese" strategy: https://www.youtube.com/watch?v=R85WVTFPmRE

Plays "normally" (cautiously since the bot is so good) until 7:00 accumulating gold for enough items to more safely eliminate the creeps: https://www.youtube.com/watch?v=R85WVTFPmRE&t=420s

Re:Positions chess engines don't understand by sillysaurusx on Tuesday May 18, 2021 @12:26AM (#27191251)
Thank you so much! I couldn’t find a video anywhere I looked, and started wondering whether I imagined the whole thing.

I think these kinds of adversarial examples will be extremely common in production models. People won’t be crafting images that fool the model into thinking you’re a stop sign; they’ll discover that when the human isn’t paying attention, you can run in front of a Tesla with a group of friends and it veers into oncoming traffic. (Terrible made-up example, but I’m pretty sure that it’s a losing game to play “can we think of all possible cases we need to train for ahead of time?”)

Re:Positions chess engines don't understand by hatsunearu on Tuesday May 18, 2021 @07:03PM (#27202428)
that's such a weird behavior, the bot completely ignores the opponent when in that particular spot?!
Re:Positions chess engines don't understand by sillysaurusx on Monday May 17, 2021 @11:10PM (#27190884)
Sadly not. I'm not sure anyone expected the bot to lose. I've been searching for where I saw it, but 2017 feels like a lifetime ago. I'll link it here if I do.

You can watch Black beat the bot in a fair game here, though, which I find immensely satisfying: https://youtu.be/qov1NXsTSbs?t=88 IIRC he was one of only like... five? (less?) who managed to win one game.