An AI art enthusiast has apparently stumbled across a creepy, recurring image – now known as Loab – which appears to be more easily generated than you'd ever expect (or want). The Internet has now dubbed Loab the first AI art cryptid.
Artificial intelligence has come a long way since the concept was pioneered by Alan Turing in the 1950s. In a nutshell, machines with artificial intelligence have been programmed in a way that allows them to mimic human intelligence - and in some cases learn and improve - in order to complete preordained tasks. AI is a cornerstone of our technology orientated modern-day lives, and in recent times it has started to make its influence known in the artistic sphere.
Scientists have created bespoke AI programs that are capable of taking prompts from humans - often in the form of plain text or images - and use them as guiding points of inspiration with which to generate art. Often, these computer generated images are chaotically random and surrealist in nature, and on occasion they have even been known to stray into the realms of the nightmarish and the creepy.
Enter Loab. Earlier this year Twitter user Supercomposite claims to have prompted the creation of an AI generated woman - that they named Loab - who ‘haunts every image that she touches’.
And remember my friend, future events such as these will affect you in the future
Abstract. We introduce AudioLM, a framework for high-quality audio generation with long-term consistency. AudioLM maps the input audio to a sequence of discrete tokens and casts audio generation as a language modeling task in this representation space. We show how existing audio tokenizers provide different trade-offs between reconstruction quality and long-term structure, and we propose a hybrid tokenization scheme to achieve both objectives. Namely, we leverage the discretized activations of a masked language model pre-trained on audio to capture long-term structure and the discrete codes produced by a neural audio codec to achieve high-quality synthesis. By training on large corpora of raw audio waveforms, AudioLM learns to generate natural and coherent continuations given short prompts. When trained on speech, and without any transcript or annotation, AudioLM generates syntactically and semantically plausible speech continuations while also maintaining speaker identity and prosody for unseen speakers. Furthermore, we demonstrate how our approach extends beyond speech by generating coherent piano music continuations, despite being trained without any symbolic representation of music.
And remember my friend, future events such as these will affect you in the future
Deepfake Audio Has a Tell – Researchers Use Fluid Dynamics To Spot Artificial Imposter Voices by Logan Blue and Patrick Traynor
September 23, 2022
Introduction:
(IFL Science) Imagine the following scenario. A phone rings. An office worker answers it and hears his boss, in a panic, tell him that she forgot to transfer money to the new contractor before she left for the day and needs him to do it. She gives him the wire transfer information, and with the money transferred, the crisis has been averted.
The worker sits back in his chair, takes a deep breath, and watches as his boss walks in the door. The voice on the other end of the call was not his boss. In fact, it wasn’t even a human. The voice he heard was that of an audio deepfake, a machine-generated audio sample designed to sound exactly like his boss.
Attacks like this using recorded audio have already occurred, and conversational audio deepfakes might not be far off.
Deepfakes, both audio and video, have been possible only with the development of sophisticated machine learning technologies in recent years. Deepfakes have brought with them a new level of uncertainty around digital media. To detect deepfakes, many researchers have turned to analyzing visual artifacts – minute glitches and inconsistencies – found in video deepfakes.
Audio deepfakes potentially pose an even greater threat, because people often communicate verbally without video – for example, via phone calls, radio and voice recordings. These voice-only communications greatly expand the possibilities for attackers to use deepfakes.