In this extra special episode, host Peter Bauman (Le Random's editor in chief) speaks with prominent AI researcher Ian Goodfellow about the legendary origins of GANs, their unexpected success and indelible impact on both twenty-first-century image making and AI research. This episode contains Peter and Ian's full conversation and serves as a companion to Monday's written interview, which covered the first half of the discussion only.Monday's editorial: https://www.lerandom.art/editorial/ian-goodfellow-on-inventing-gansChapters 📖:[00:00:03]: Introduction and cultural impact of GANs[00:03:30]: Ian explains GANs and game theory[00:06:12]: The Montreal origin story begins[00:10:51]: The first GAN and MNIST success[00:19:36]: Early reception and longevity surprises[00:21:22]: LAPGAN and DCGAN mark takeoff[00:23:54]: Is generative modeling deep learning’s culmination?[00:26:11]: Can GANs be creative or just mimic?[00:29:30]: GANs as tools; human creativity’s role[00:37:14]: On autonomous AI artists and personhood[00:41:50]: GANs’ role in text-to-image’s emergence[00:42:20]: Story from probabilistic graphs to media generation[00:51:30]: Key GAN advances: LAPGAN to StyleGAN and beyond[00:57:52]: Are engineers artists? [01:02:26]: Expected uses, misuse risks, and simulations[01:06:50]: Scale’s legacy, spending, and scaling laws[01:11:31]: AGI timelines and being wrong both ways[01:19:14]: Platonic representations across modalities[01:23:49]: Closing thanks and farewells

Ver todos los episodios