C# using a Local Language Model with LM Studio to Sort Screenshots
Learn how to use a local language model with C# and LM Studio to automatically sort screenshots into categories using AI and Vision Language Models (VLM). Utilize the power of visual recognition with .NET!
Using the Model Context Protocol (MCP) with C#
With the new MCP C# SDK, developers can efficiently manage communication between AI models and applications.
Anthropic’s Model Context Protocol (MCP) is currently making waves. It's a standardized protocol designed to streamline communication between applications and models by offering a structured way to exchange context and data between AI models and their clients. Whether you're developing AI-powered applications or integrating multiple models into a cohesive system, MCP ensures interoperability and scalability.
LLM Temperature Explained
Temperature is a key parameter in large language models (LLMs) that controls the randomness of generated text. It adjusts the probability distribution used when predicting the next token in a sequence. A lower temperature makes the model more deterministic, favoring highly probable tokens and producing more consistent, coherent outputs — ideal for factual or technical tasks. A higher temperature increases randomness by allowing the selection of less probable tokens, leading to more varied and creative responses, though sometimes at the cost of coherence.
AI Tools Are Hallucinating Software Dependencies – And Cybercriminals Are Taking Advantage
Discover how AI-generated code from large language models (LLMs) is introducing new cybersecurity risks through hallucinated software dependencies and slopsquatting. Learn how attackers exploit these vulnerabilities and what developers can do to stay safe.
Exploring the Next Level of AI Image Generation with OpenAI's GPT-4o
The world of AI-generated images has reached a new frontier with the release of OpenAI's latest model, GPT-4o. Unlike previous iterations, GPT-4o seamlessly integrates advanced image generation capabilities, producing highly detailed, contextually accurate, and incredibly realistic visuals. One of the most groundbreaking advancements in this model is its ability to generate photorealistic images that rival human-created photography. This leap forward opens up unprecedented possibilities across industries such as marketing, design, entertainment, and education.
DeepSeek JailBrake Attack
The Chinese government is famous/notorious for its censorship. The Chinese LLM DeepSeek naturally follows this attitude and does not talk about content that is sensitive for China's leadership, such as Tiananmen Square Massacre, Taiwan or the Cultural Revolution. With some simple JailBrakeing you can get DeepSeek to bypass the censorship.