Watermarking will be a necessary trick to sift through the chaos of AI-generated content in the future. Authors: John Kirchenbauer, Jonas Geiping, Yuxin Wen Jonathan Katz, Ian Miers, Tom Goldstein from University of Maryland Link to paper: https://
arxiv.org/pdf/2301.10226
.pdf
…
SAFETY
-
Watermarking: a necessary trick for AI-generated content
By
–
-
AI systems alerted to avoid synthetic data to prevent recursive training problem
By
–
More importantly, it can alert the AI systems themselves not to train on "synthetic data", which could help solve the recursive AI data problem (AI training itself on it's own output, AKA the machine learning version of eating your own vomit)
-
Watermark selects whitelist tokens and promotes them during sampling
By
–
The watermark works by selecting a randomized set of “whitelist” tokens before any text is generated, and then softly promoting use of those tokens during sampling. (a token can be a letter, word, numbers, punctuations or any other string that is useful for the specific task)
-
Watermarking detects AI-generated text for readers and academia
By
–
These cryptic text signatures are indiscernible to the average reader, but reliably detectable by the algorithm. Watermarking can alert you when you're reading a web article that was AI generated (sorry, CNET) or be used in academia to detect "AI Plagiarism"
-
Watermarking AI text to detect ChatGPT-generated content
By
–
"Watermarking" AI-generated text. Researchers from University of Maryland propose a way to discretely embed (and detect) special tokens in order to accurately determine whether or not text was generated from something like ChatGPT. ↓
-
Concerns About Irresponsible Release of Large Language Models
By
–
Sharing with everyone what I have been repeating to media and interested parties since the last months: it was irresponsible to release a large language model that still has severe limitations – and there are others even superior to it #ChatGPT #GPAI @GPAI_PMIA @OECDEduSkills
-
Waymo Autonomous Vehicle Stuck in San Francisco Intersection
By
–
@melon6ix Hello. Could you chat briefly about the Waymo car that was stuck in the San Francisco intersection yesterday? Thanks, Cade Metz, The New York Times, 510-325-0717
-
AI-Generated Text Watermarking: Detection Methods and Bypassing Techniques
By
–
Si os preguntáis cómo funcionaría un sistema de marca de agua que sirva para detectar si un texto ha sido generado por una IA, este hilo (y paper) lo explica muy bien. El problema es que mientras lo leo mi intuición me dice que es una medida muy fácil de sortear…
-
ChatGPT Reports Perfect, But Humans Tell Powerful Stories
By
–
You may get ChatGPT to create perfect reports,
You’ll always need humans to tell powerful stories. -
Voice Cloning Technology: Innovation Sparks Ethical Debate
By
–
1º (Acción) Aparecerá un buen modelo (e.g. VALL·E 2) capaz de clonar voz con poco entrenamiento y buena calidad. La gente empezará a experimentar. 2º (Reacción) Se abren los debates. Se criticará a las empresas que por abaratar costes usen estas tecnologías y muchas no lo harán.