GAN
Generative Adversarial Network: a generative model trained via a competition between a generator and a discriminator (adversarial loss).
As defined in Gwern — Anonymous writer who predicted AI trajectory on $12K/year salary
Where it comes up · 3
- Gwern — Anonymous writer who predicted AI trajectory on $12K/year salary3 claims
- Tech and Consumer Growth Investing1 claim
- Jeremiah Lowin: Explaining the New AI Paradigm - [Invest Like the Best, EP.307]1 claim
Most important claims · 5 of 5Search all claims for “GAN” →
- GAN and diffusion models think differently because of their loss functions: GANs face an adversarial loss giving them an incentive to hide difficult things, so they are 'scared' and put hands off-screen and can't think about them, whereas diffusion models have no such incentive and do attempt hands, producing monstrous Cthulhu-esque distortions instead.Gwern — Anonymous writer who predicted AI trajectory on $12K/year salary
- Many correct deep-learning ideas existed early but failed for lack of compute to train them at scale; ResNets worked when published around 1988 but only at irrelevantly small scale and were forgotten until 2015, and BigGAN's success at 300 million images shows GANs scale, contradicting people who still claim GANs cannot scale past millions—demonstrating that abundant GPUs, not algorithms, are the common ingredient.Gwern — Anonymous writer who predicted AI trajectory on $12K/year salary
- Earlier GAN models were easy to explore because their latent dimensions corresponded closely to observable output attributes, so users could literally dial smile, hair length, glasses, or gaze direction by changing a single number along that dimension.Jeremiah Lowin: Explaining the New AI Paradigm - [Invest Like the Best, EP.307]
- Excluding capability, AI models are already far more cognitively diverse than humans: different architectures (LLMs, GANs, VAEs, image generators) have wildly different latent spaces, artifacts and errors—some as different from each other as ants from beavers—whereas humans are quite similar in writing and attitude; within recent LLMs diversity has collapsed because everyone trains on the same data like identical twins, but across deep learning broadly there is a range of minds not found in any philosophy-of-mind paper.Gwern — Anonymous writer who predicted AI trajectory on $12K/year salary
- A breakthrough in algorithms such as GANs or CNNs that reduces dependence on data scale would likely reintroduce mean reversion within technology.Tech and Consumer Growth Investing