We make a #generator and a #discriminator fight. A lot. " In a #GAN, two #NeuralNetworks compete with each other in the form of a #ZeroSumGame, where one agent's gain is another agent's loss " #GenerativeAdversarialNetwork
For awhile I would clarify I am not talking about a #LargeLanguageModel , I am talking about a #GenerativeAdversarialNetwork en.wikipedia.org/wiki/Generat... But honestly, but that's just because I'm a game theory aficionado who thinks Generative Adversarial Network is a cool term. #LLM #GAN

Generative adversarial network...
Generative adversarial network - Wikipedia

When appropriate I try to use the right term: #MachineLearning #LargeLanguageModel #GenerativeAdversarialNetwork I find myself putting "AI" in quotes when I type it. It does not understand, it does not think, it is not conscious, its job is to #replicate to #simulate to guess, probabilistically
So not your recommended tools for making things better, but what about all the people seeking to make things worse? Would a #LargeLanguageModel / #LLM be right for them? Or perhaps a #GenerativeAdversarialNetwork / #GAN, could one of those help someone make things worse, faster?
Backbone 1.5 with DrumGAN by Sony Computer Science Laboratory | Backbone 1.5

YouTube
PassGAN: KI knackt gängige Passwörter unter einer Minute

Laut einer Studie von Home Security Heroes können ca. 51 Prozent aller gängigen Passwörter von einer KI wie PassGAN geknackt werden.

Tarnkappe.info
Universelle, durchschnittlich wirkende Gesichter können laut einer Studie als "Master Faces" Systeme für die Gesichtserkennung recht einfach austricksen.
Forscher entdecken Generalschlüssel für Systeme zur Gesichtserkennung
Forscher entdecken Generalschlüssel für Systeme zur Gesichtserkennung

Universelle, durchschnittlich wirkende Gesichter können laut einer Studie als "Master Faces" Systeme für die Gesichtserkennung recht einfach austricksen.

Twitter bans deepfakes, but only those ‘likely to cause harm’ - Twitter isn't interested in how the “synthetic or manipulated” media is created, but if it has the... more: https://nakedsecurity.sophos.com/2020/02/06/twitter-bans-deepfakes-but-only-those-likely-to-cause-harm/ #generativeadversarialnetwork #machinelearning #socialnetworks #disinformation #shallowfakes #cheapfakes #thecurrent #assembler #deepfakes #fakenews #alphabet #facebook #stylegan #twitter #google #jigsaw
Twitter bans deepfakes, but only those ‘likely to cause harm’

Naked Security