# watermarking A technique for embedding detectable signals in AI-generated text to help determine whether the text originated from a language model. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## AI model watermarking changes agent behavior DevFeed: [AI model watermarking changes agent behavior]() Original publisher: [Read original article]() Author: Thomas Claburn Published: 2026-09-17T13:00:00Z Content type: news Language: en Sources: [www.theregister.com - Articles]() Topics: [watermarking](), [Artificial Intelligence]() Tags: [agent](), [ai](), [ai-and-ml](), [ai-watermarking](), [anthropic](), [model](), [prompt-injection](), [synthid](), [watermarking]() ### AI overview Lasso Security reports that AI model watermarking is associated with differences in agent tool handling and model refusals. ### Source excerpt Lasso Security sees differences in tool handling and model refusals ## How does Claude watermark text? DevFeed: [How does Claude watermark text?]() Original publisher: [Read original article]() Author: Dr. Ashish Bamania Published: 2026-08-24T15:20:14Z Content type: tutorial Language: en Sources: [Dr. Ashish Bamania]() Topics: [Claude](), [watermarking](), [anthropic](), [Large Language Model](), [tokenization]() Tags: [anthropic](), [artificial-intelligence](), [claude](), [data-science](), [llms](), [programming](), [software-engineering](), [technology](), [tokens](), [watermarking]() ### AI overview A visual tutorial explains how Anthropic plans to watermark and detect text generated by Claude models, and introduces token-by-token text generation, token IDs, embeddings, logits, and probabilities. ### Source excerpt A visual lesson to clearly understand how Anthropic watermarks and detects Claude-generated text. Continue reading on Level Up Coding " ## How Anthropic Watermarks Claude-Generated Text DevFeed: [How Anthropic Watermarks Claude-Generated Text]() Original publisher: [Read original article]() Author: Dr. Ashish Bamania Published: 2026-08-20T00:04:24Z Content type: tutorial Language: en Sources: [Into AI]() Topics: [Claude](), [watermarking](), [anthropic](), [Large Language Model]() Tags: [anthropic](), [claude](), [watermarking]() ### AI overview A tutorial explains how Anthropic watermarks text generated by Claude. It describes next-token generation and a sampling-based watermarking process that changes token selection without additional LLM training. ### Source excerpt Visually understand how Anthropic watermarks and detects Claude-generated text. ## Our approach to bioresilience DevFeed: [Our approach to bioresilience]() Original publisher: [Read original article]() Author: Google DeepMind; Isomorphic Labs Published: 2026-07-16T09:30:42Z Content type: article Language: en Sources: [Google DeepMind News]() Topics: [AI Models](), [Artificial Intelligence](), [Google](), [Frontier AI](), [synthid](), [Security](), [watermarking](), [Monitoring]() Tags: [agents](), [ai](), [ai-models](), [frontier-ai](), [gemini](), [global](), [google](), [health](), [models](), [partners](), [research](), [responsibility-safety](), [safety](), [security](), [synthid](), [watermarking]() ### AI overview Google DeepMind and Isomorphic Labs outline a joint bioresilience program that uses AI models and agents to help prevent misuse, detect outbreaks and support responses to biological threats. The approach combines partnerships, model safety measures and tools such as SynthID with applications in protein structure prediction, drug design and genome research. ### Source excerpt Google DeepMind and Isomorphic Labs are sharing our joint approach to bioresilience and AI models. ## Advancing content provenance for a safer, more transparent AI ecosystem DevFeed: [Advancing content provenance for a safer, more transparent AI ecosystem]() Original publisher: [Read original article]() Published: 2026-05-19T10:45:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [Artificial Intelligence](), [OpenAI](), [synthid](), [watermarking](), [API](), [ChatGPT](), [Google]() Tags: [ai](), [api](), [chatgpt](), [content](), [ecosystem](), [google](), [images](), [media](), [openai](), [safety](), [synthid](), [update](), [watermarking]() ### AI overview OpenAI describes an ecosystem-based approach to content provenance for AI-generated media, combining Content Credentials, C2PA standards, SynthID watermarking, and verification tools. The July 31, 2026 update extends SynthID watermarking and verification to supported audio and adds API access for provenance checks. ### Source excerpt OpenAI advances AI content provenance with Content Credentials, SynthID, and a verification tool to help people identify and trust AI-generated media. ## Making it easier to understand how content was created and edited DevFeed: [Making it easier to understand how content was created and edited]() Original publisher: [Read original article]() Author: Laurie Richardson Published: 2026-05-17T13:43:50Z Content type: article Language: en Sources: [Google DeepMind News]() Topics: [synthid](), [Artificial Intelligence](), [watermarking](), [Chrome](), [Web](), [Cloud]() Tags: [ai](), [chrome](), [cloud](), [gemini-in-chrome](), [none](), [products](), [synthid](), [watermarking](), [web]() ### AI overview Google DeepMind describes expanded tools for verifying how digital content was created and edited. The update extends SynthID watermark verification and C2PA Content Credentials across Gemini, Search, Chrome, Pixel phones and Cloud, helping users identify AI-generated media and determine whether content is original or modified. ### Source excerpt We're expanding our tools to help you understand how content was created and edited across the web. ## Visible Watermarking with Gradio DevFeed: [Visible Watermarking with Gradio]() Original publisher: [Read original article]() Author: Margaret Mitchell Published: 2025-09-15T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [watermarking](), [gradio](), [hugging face](), [Artificial Intelligence](), [Generative AI]() Tags: [ai-content](), [ai-transparency](), [building](), [ethics](), [gradio](), [guide](), [hugging-face](), [open-source](), [text-generation](), [text-to-image](), [text-to-video](), [watermarking]() ### AI overview Hugging Face explains how Gradio can add visible watermarks to AI-generated images, video, and text in Spaces. The article highlights filename-based, open-image, NumPy-array, QR, custom text, and chatbot watermarking options to support attribution, transparency, and disclosure. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Open Source Developers Guide to the EU AI Act DevFeed: [Open Source Developers Guide to the EU AI Act]() Original publisher: [Read original article]() Author: Bruna Trevelin; Lucie-Aimée Kaffee; Yacine Jernite Published: 2024-12-02T00:00:00Z Content type: tutorial Language: en Sources: [Hugging Face - Blog]() Topics: [Responsibility & Safety](), [Open Source](), [watermarking](), [dataset]() Tags: [ai](), [compliance](), [critical-infrastructure](), [data](), [ethics](), [eu](), [guide](), [open-source](), [policy](), [responsible-ai](), [safety](), [watermarking]() ### AI overview A guide for open source developers on how the EU AI Act may apply to AI systems and models. It explains that obligations vary by model type, release context, role, and risk level, and highlights documentation, model and dataset information, deployment disclosures, copyright, privacy, opt-out mechanisms, and personal-data redaction. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## Introducing SynthID Text DevFeed: [Introducing SynthID Text]() Original publisher: [Read original article]() Author: Sumedh Ghaisas; Sumanth Dathathri; Ryan Mullins; Joao Gante; Marc Sun; Raushan Turganbay Published: 2024-10-23T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [synthid](), [watermarking](), [Large Language Model](), [configuration](), [API]() Tags: [announcement](), [api](), [artificial-intelligence](), [configuration](), [llm](), [open-source](), [research](), [synthid](), [technical](), [watermarking]() ### AI overview Introducing SynthID Text, a watermarking technique for AI-generated text. It augments LLM generation with an imperceptible watermark that trained models can detect, while aiming to preserve generation quality and work without modifying the underlying LLM. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. ## The Render Token DevFeed: [The Render Token]() Original publisher: [Read original article]() Author: Brendan Eich Published: 2017-09-25T14:57:39Z Content type: opinion Language: en Sources: [Brendan Eich]() Topics: [render](), [GPU](), [Blockchain](), [watermarking](), [Security](), [Testing](), [Ethereum](), [proof of work]() Tags: [blockchain](), [ethereum](), [gpu](), [proof-of-work](), [render](), [security](), [testing](), [uncategorized](), [watermarking]() ### AI overview Brendan Eich discusses OTOY's RNDR token as a decentralized GPU-cloud rendering system for AR/VR, games, and movies. He describes token-based access to computing resources, blockchain-attested work verification, renderer reputation, hardware-assisted confidentiality, and watermarking for protecting digital models and art. ### Source excerpt I wrote about OTOY over four years ago, in "Today I Saw The Future". Since then, I have been inspired by the commitment of the founders Jules Urbach and Alissa Grainger to the vision that Jules enunciates: "... to render and remix simulated reality as effortlessly as the web did for text and digital media. ... Continue reading "The Render Token" ## The Two-Dimensional Fourier Transform and Digital Watermarking DevFeed: [The Two-Dimensional Fourier Transform and Digital Watermarking]() Original publisher: [Read original article]() Published: 2013-12-30T19:24:05Z Content type: tutorial Language: en Sources: [Jeremy Kun]() Topics: [fourier transform](), [watermarking](), [Algorithm](), [Code]() Tags: [algorithm](), [animations](), [big-o-notation](), [calculus](), [dimension](), [fft](), [fourier-analysis](), [fourier-transform](), [github](), [graphics](), [image-manipulation](), [images](), [james-hance](), [mathematics](), [matrices](), [programming](), [python](), [star-wars](), [up](), [watermarking]() ### AI overview This tutorial introduces the multidimensional Fourier transform, explains its relationship to the one-dimensional transform, describes an FFT-style algorithm for computing it, and applies it to digitally watermarking images. ### Source excerpt We've studied the Fourier transform quite a bit on this blog: with four primers and the Fast Fourier Transform algorithm under our belt, it's about time we opened up our eyes to higher dimensions. Indeed, in the decades since Cooley & Tukey's landmark paper, the most interesting applications of the discrete Fourier transform have occurred in dimensions greater than 1. But for all our work we haven't yet discussed what it means to take an "n-dimensional" Fourier transform.