-
Enabling My AI Agent to Build and Run Its Own Tools
I have a custom AI Agent with tools that you can read about in this post. I started with a few basic tools (web, search and weather) but was thinking about a command line tool from the start and the possibility to even build its own tools. So when the AI Agent felt mature, i […]
-
The road to Azure AI Engineer Associate
So I have worked with OpenAI models in Azure and wanted to gain a broader insight into the different Azure AI Services. The AI-102 exam looked like a good fit because it covers a comprehensive range of services and skills in depth. I started in September, and from the start, it took around 4 months. […]
-
How I Built a Custom AI Agent with Tools from Scratch
Even though there are existing frameworks for AI Agents, I had an idea for a rather easy way of building a custom AI Agent from scratch and decided to try it out. Autonomous Agent with Tools I specify tools for an LLM that functions as an Agent. A console app executes these tools based on […]
-
Securing AI: Mitigating Prompt Injection Attacks with Azure AI Prompt Shields
Large Language Models (LLMs) are powerful but vulnerable to attacks that manipulate their behavior. Azure AI Content Safety’s Prompt Shields API provides a critical defense against these threats, and it has a free pricing tier that covers a few thousand calls a month. Go to the example code below. The Threat Landscape: Two Main Attack […]
-
Hands-On with Gemini 2.0 Flash API: Blazing-Fast AI in Open WebUI
You can now try out Google’s latest AI model, Gemini 2.0 Flash (experimental), directly in Google AI Studio or by using your own local GUI in Open WebUI. To connect to the API through a pipeline in Open WebUI, follow these steps: My initial impression is that it handles both coding and text well, and […]
-
First Impressions: Setting Up My AI-Ready Laptop
So I picked up a gaming laptop on Black Friday to use as an AI PC for running local LLMs, trying out image generation, agentic flows, and possibly video and speech processing. Additionally, I’ll be using it for non-AI tasks like video editing and general use. I bought an MSI Cyborg 14 with an RTX […]
-
Advancing AI Reasoning: OpenAI’s o1 Model
In the dynamic field of artificial intelligence, OpenAI has introduced an exciting development with its latest model, OpenAI o1. This large language model (LLM) is designed to excel in complex reasoning tasks, offering a fresh perspective on AI capabilities. Trained with reinforcement learning, o1 can think critically, producing a detailed chain of thought before delivering […]
-
AI Evolution: Preparing for the Opportunities and Challenges Ahead
The rapid evolution of AI has led some to question the value of an education, long-term savings, or even taking a mortgage to buy a house. They worry that AI might soon replace jobs, reach Superintelligence and either create a Utopia or a Doomsday for mankind. Such concerns are fueled by philosophers like Nick Bostrom, […]
-
AI’s Impact on the Environment from Now to 2030
Will AI cause more problems for the environment in the next 6 years than solutions? Wells Fargo is projecting that AI power demand will grow 8100% from 8TWh in 2024 to 652TWh in 2030. More than half of that is due to AI model training. Google has already stated that AI data centers are derailing […]
-
AI-Generated Content: A Looming Threat to LLM Quality?
Is there a risk of a recursive degradation effect for LLMs over time due to training on subpar AI-generated content from the web? Some estimates say that around 50% of all content on the web is now AI-generated, and that could rise to 90% by 2026. A more precise number depends on the methodology used […]