Elon Musk: Run a physics sim long enough & you’ll get intelligence
2669 replies, 103591 likes
Janelle Shane: When machine learning is astonishing - I collected some highlights from a paper on algorithmic creativity
35 replies, 3008 likes
Janelle Shane: Sometimes machine learning solves the wrong problem in unintentionally sinister ways. https://t.co/oUN2UclQg3
7 replies, 521 likes
Jamie Bartlett: This is from an Atlantic article, about this paper: https://arxiv.org/pdf/1803.03453.pdf, which is VERY interesting - it's a collection of anecdotes of accidental creativity in algorithms. (Includes this good tic-tac-toe story, also mentioned in @TomChivers recent book). https://t.co/cokPaHYs71
3 replies, 322 likes
hardmaru: Found this recent paper by Tom Everitt and Marcus Hutter that looks at the topic of RL agents “cheating” from an AI Safety perspective. Worth a look!
Blog https://link.medium.com/yX1b3UXERZ https://t.co/cak1IUTAlM
3 replies, 121 likes
𝔊𝔴𝔢𝔯𝔫: In many areas, there is a 'brute force' approach. It's often pretty unpopular. Doesn't mean it's wrong, though... [genetics/statistics/AI/economics/politics-ethics/philosophy/science] :: [bigger GWASes/Monte Carlo/more GPUs/capitalism/economic growth/atomism/reductionism].
1 replies, 83 likes
Janelle Shane: I notice people are retweeting this thread again - if you find this stuff as fascinating as I do, I definitely have a book for you: https://aiweirdness.com/books
1 replies, 29 likes
Jean-Baptiste Mouret: @AndrewM_Webb @hardmaru We observe this kind of things a lot when evolving robots or robot controllers / morphology. See https://arxiv.org/abs/1803.03453 for many examples.
0 replies, 13 likes
jonathanstray: I was lucky enough to be introduced to reward hacking when I saw Karl Sims' 1994 "Evolving Virtual Creatures" paper presented at SIGGRAPH. He showed examples of creatures cheating in hilarious ways, such as by falling over to "move" a long distance.
1 replies, 11 likes
Physics Today: Joel Lehman et al point out that sometimes with ML/AI, the algorithms are too smart for their own good, such as deciding that crashing a plane into the ground is the most efficient way of landing it. H/T @JamieJBartlett
1 replies, 6 likes
Machine Learning Failures: Neural networks evolved to classify edible and poisonous mushrooms took advantage of the data being presented in alternating order, and didn't actually learn features of the input images. (from https://arxiv.org/pdf/1803.03453.pdf)
0 replies, 5 likes
stoey: @GarethJennings3 @CherylRofer @luke_j_obrien Anyone wanting to give AI/Machine Learning a decision making position should be required to read this paper first: https://arxiv.org/pdf/1803.03453.pdf
Nice summary thread of it here:
0 replies, 4 likes
eigenrobot: @politicalmath @jaspar :) https://twitter.com/JanelleCShane/status/984809679040598016
1 replies, 4 likes
Natalie D Kane: Link to original paper here: 'The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities' https://arxiv.org/pdf/1803.03453.pdf
0 replies, 3 likes
Kevin J. Brennan: A perfect example of how the metrics you choose distort the outcomes you get.
0 replies, 2 likes
Liminal Warmth 🌸: Mostly what this thread tells me is that we need fewer bugs in the physics of our robot training simulators.
0 replies, 1 likes
will: @hikari_no_yume Oh, I absolutely *love* these stories. You might be interested in this: https://arxiv.org/abs/1803.03453
0 replies, 1 likes
Henrik Korsgaard: AI must read IMO
The Surprising Creativity of Digital Evolution: A Collection of Anecdotesfrom the Evolutionary Computation and Artificial Life Research Communities
"creative" in research perhaps -- destructive and highly problematic in production
1 replies, 1 likes
101 144 141 155 040 105 154 153 165 163: @MoralHazardPay @antimule @LightningShade0 this is especially true because machine learning/evolutionary computation systems have a nasty habit of doing things like crashing the physics engine to give themselves more juice or inducing memory bombs to beat opponents
2 replies, 0 likes
Alasdair Allan: An intriguing paper, "A Collection of Anecdotes
from the Evolutionary Computation and Artificial Life Research Communities," https://arxiv.org/pdf/1803.03453.pdf. #MachineLearning
1 replies, 0 likes
Found on Feb 15 2020 at https://arxiv.org/pdf/1803.03453.pdf