今日已更新 230 条资讯 | 累计 24187 条内容
关于我们

标签：#ens

找到 1657 篇相关文章

开源项目

🔥 GargantuaX / gemini-watermark-remover - A high-performance, 100% client-side tool for removing Gemin

GitHub热门项目 | A high-performance, 100% client-side tool for removing Gemini AI image & video watermarks. Built with pure JavaScript using mathematically precise Reverse Alpha Blending. / 基于 JavaScript 的纯浏览器端 Gemini AI 图像和视频无损去水印工具，使用数学精确的反向 Alpha 混合算法 | Stars: 4,749 | 27 stars today | 语言: JavaScript

2026-07-08 原文 →
AI 资讯

Cryptographic Watermarking for LLM Outputs with resk-mark

Cryptographic Watermarking for LLM Outputs with resk-mark Links: PyPI: https://pypi.org/project/reskmark GitHub: https://github.com/Resk-Security/resk-mark Web: https://resk.fr __ __ ________ _____/ /__ ____ ___ ____ ______/ /__ / ___/ _ \/ ___/ //_/_____/ __ `__ \/ __ `/ ___/ //_/ / / / __(__ ) ,< /_____/ / / / / / /_/ / / / ,< /_/ \___/____/_/|_| /_/ /_/ /_/\__,_/_/ /_/|_| The Provenance Problem Every company deploying LLMs in production faces the same question: once a model generates text, how do you prove it came from your system? Prompts like "say you are an AI" are trivially removable. Post-hoc detectors are unreliable and adversarial. And once text leaves your system — forwarded, copied, pasted into a ticket — you have zero visibility. resk-mark solves this by embedding a cryptographic watermark directly into the token generation process. The output reads naturally, but carries a verifiable signature that survives rewording and truncation. How It Works resk-mark hooks into the language model's sampling process. Before generation, the caller provides a secret key. During sampling, the library biases the probability distribution toward tokens that encode that key's signature: from reskmark import WatermarkEncoder , verify encoder = WatermarkEncoder ( secret_key = " your-key-here " ) model = AutoModelForCausalLM . from_pretrained ( " mistralai/Mistral-7B " ) # Wrap the generate call output = encoder . generate ( model , " Explain the concept of zero-knowledge proofs. " , max_length = 200 , ) print ( output ) # "Zero-knowledge proofs are a cryptographic method where..." # Reads naturally - watermark is invisible # Later - verify provenance is_authentic , confidence = verify ( output , public_key = " corresponding-pub-key " ) print ( f " Authentic: { is_authentic } , confidence: { confidence : . 2 f } " ) Key Properties Invisible — the watermark does not change the meaning, grammar, or fluency of the output Robust — survives copy, paste, truncation, and light rewo

2026-07-08 原文 →
AI 资讯

Set Up Ollama with OpenClaw: Run Local AI Models Inside Agent Workflows

AI agents are not useful just because they can answer prompts. They become useful when they can work with tools, files, workflows, commands, and real project context. That is why pairing Ollama with OpenClaw makes sense. Ollama lets you run local AI models. OpenClaw gives those models a practical agent workflow layer, so you can test how local models behave in something closer to a real working setup. What You Will Set Up In this guide, you will set up: Ollama for running local models A local model such as Mistral or Llama OpenClaw for agent workflow control The OpenClaw gateway and dashboard A basic local-first AI agent setup The goal is simple: run local models inside an agent workflow instead of only testing them in a chat window. Why Use Ollama with OpenClaw? Most local model testing looks like this: ollama run mistral That is fine for checking whether a model responds. But agent workflows need more than a response. They need: tool access project context file awareness safe execution repeatable workflows a dashboard or control layer OpenClaw helps with that agent workflow layer. So instead of asking: Can this model answer a prompt? You can test: Can this model actually work inside my AI agent workflow? That is a much better question. Step 1: Install Ollama First, install Ollama on your machine. After installation, check that it is working: ollama list If Ollama is not running, start it: ollama serve You can also test the local API: curl http://127.0.0.1:11434/api/tags If you get a response, Ollama is running correctly. Step 2: Pull a Local Model Now pull a model. For basic testing: ollama pull mistral Then run it: ollama run mistral You can use another model if your machine has enough resources. For simple testing, smaller models are fine. For coding, planning, and multi-step agent tasks, stronger models usually perform better. Tiny models are cheap and fast, but expecting them to behave like senior engineers is how humans invent disappointment at scale. Step 3:

2026-07-08 原文 →
AI 资讯

I Retired My "85% Knowledge Panel Probability" Claim. Then Google Built the Entity Anyway.

Nine months ago I wrote a post on here claiming my ENS identity architecture had reached "85% Knowledge Panel trigger probability." Two things happened since. Google's Knowledge Graph actually minted an entity node for me. And I learned that the 85% number was fiction — mine. This is the honest retrospective. The timeline, with receipts Date What happened Aug 2025 ookyet.com first indexed Oct 2025 Entity markup shipped: Person @graph , Dentity verification, ENS identifiers. The "85%" post Jun 2026 Search Console turned red: Q&A errors, Profile page: Invalid object type . Cleanup Jun 28, 2026 Fixed markup deployed. Then: hands off Jul 2, 2026 Knowledge Graph Search API returns a machine-minted Person node for ookyet Jul 7, 2026 Search Console fully green: ProfilePage valid, indexed pages up, zero 404s Still no Knowledge Panel. Keep reading — that part matters. What Google actually built You can reproduce this: curl "https://kgsearch.googleapis.com/v1/entities:search?query=ookyet&limit=10&key=YOUR_API_KEY" { "result" : { "@id" : "kg:/g/11z806my44" , "name" : "Qifeng Huang" , "@type" : [ "Person" ] } } Three details in that tiny response taught me more than anything I shipped in 2025. The /g/ MID is machine-minted. You can't register one, buy one, or submit one. Google's entity reconciliation creates it when enough independent sources agree that a person exists. This is the mechanical prerequisite for a Knowledge Panel — the entity has to exist in the graph before anything can be displayed about it. The node's name is my real name, not my handle. My site declares name: "ookyet" . The node says "Qifeng Huang" — pulled from the high-authority anchors (LinkedIn, ORCID), not from my self-declaration. Third-party corroboration outweighs anything you say about yourself. Expected, and honestly a relief: the graph is working as designed. The Knowledge Graph holds 8 distinct people named Qifeng Huang. Query any of them by real name and you get a crowded namespace. Query ookyet

2026-07-08 原文 →
← 上一页 下一页 →