Is it the number of examples that matters or the number of presentations to the model during training? E.g. humans used spaced repetition to memorize facts but there are no equivalents of similar techniques in LLMs where the typical training regime is uniform random.
RESEARCH
-
Stanford HAI Spring Conference 2023: AI, Creativity, Policy
By
–
A sneak preview of the @StanfordHAI Spring Conference 2023 – AI, generative models, arts, creativity, policy, regulation, and more! Stay tuned and sign up to our mailing list: https://
hai.stanford.edu/subscribe-hai-
mailing-list
… -
AI Correctness vs User Satisfaction: Resolving HCI Conflicts
By
–
Another wonderful panel by @msbernst @stanfordmav @adapperprof @landay @StanfordHAI Fall Conf today. “AI optimizes for 100% correctness; HCI optimizes for 100% user satisfaction. What happens when they’re in conflict?”
-
Galática’s fastai notebook plan exploration attempt
By
–
Looks like http://
galatica.org had a good plan for a fastai notebook, although I can't get it to go further than producing this intro! 😀 -
Turing Test Criticism: Rethinking AI Evaluation Standards
By
–
very fair criticism! i meant it as a joke about how i think people are (correctly) realizing the turing test is a bad test. i regret the tweet, but i'll leave it up in the spirit of leaving my Ls.
-
Robot Dog Walks on Stools Using Onboard Vision
By
–
New work from @berkeley_ai and @CMU_Robotics on visual locomotion enables a robot dog walking on tall bar stools in @ashishkr9311's living room — entirely from onboard cameras and compute. Trained in simulation and deployed directly in the real world!https://t.co/kBEpOCsRob https://t.co/wVIeiMgfd2
— Berkeley AI Research (@berkeley_ai) 15 novembre 2022New work from @berkeley_ai and @CMU_Robotics on visual locomotion enables a robot dog walking on tall bar stools in @ashishkr9311
's living room — entirely from onboard cameras and compute. Trained in simulation and deployed directly in the real world! http://
vision-locomotion.github.io -
Physics Laws: Brain-Dependent Perspectives on the Universe
By
–
The laws of physics reduce the universe to something our brains can deal with. For different brains (e.g., AIs) they would probably look very different.
-
Classical Mechanics as MAP Approximation of Quantum Mechanics
By
–
Classical mechanics is the MAP approximation of quantum mechanics.
-
Feigenbaum on Most Important AI Conference Topic
By
–
“The topic of this conference is the most important topic of AI!” — Ed Feigenbaum, Turing Award winner (1994), luminary of @StanfordAILab , and a dear friend and mentor