How are they build?

Imagine you’re trying to learn a new language. You wouldn’t just read a few sentences, right? You’d immerse yourself in books, articles, conversations – anything you could get your hands on. That’s essentially what LLMs do. They devour tons of text from the internet, like books, articles, and websites. The more they read, the better… Continue reading How are they build?

Published
Categorized as AI

What are Large Language Models (LLMs)

Large language models (LLMs) represent a significant leap forward in artificial intelligence, demonstrating a remarkable ability to process and generate human language. At their core, these sophisticated systems are powered by deep learning architectures, most notably the transformer network. This architecture, drawing inspiration from the intricate workings of the human brain, allows LLMs to effectively… Continue reading What are Large Language Models (LLMs)

Published
Categorized as AI

Calculating the performance of AI models

Calculating the performance of AI models, especially large language models (LLMs) and other generative models, is a complex task. There’s no single metric that captures everything, and the best approach depends heavily on the specific model and its intended use. Here’s a breakdown of common methods: 1. Traditional Metrics (for Classification and Regression): 2. Metrics… Continue reading Calculating the performance of AI models

Published
Categorized as AI

A Solid Performer: My PC’s Experience with Large Language Models

Recently, I had the opportunity to test my PC’s capabilities by running ollama run deepseek-r1:32b, a large language model with 32 billion parameters. This presented a significant workload, and I was interested in observing how my system handled it. Observations on System Performance Running such a large model provides valuable insights into a system’s strengths.… Continue reading A Solid Performer: My PC’s Experience with Large Language Models

Published
Categorized as AI

The AI Revolution: From Cloud to Desktop

AI system is a computer program designed to mimic human cognitive functions, such as learning, reasoning, problem-solving, perception, and language understanding. All these systems leverage a range of techniques, including machine learning, deep learning, and natural language processing, to achieve their objectives.   Artificial intelligence (AI) has transcended the realm of science fiction and become… Continue reading The AI Revolution: From Cloud to Desktop

Published
Categorized as AI

Which AI search engines is best to generate source code?

The “best” solution will heavily depend on several factors: Complexity of the desired code: Simpler code generation tasks might be handled efficiently by some of the AI search engines like YOU.com or Bing AI, which offer functionalities like basic code snippets or summaries. Bing AI and Google Search with Gemini are the best options. In most… Continue reading Which AI search engines is best to generate source code?

Published
Categorized as Code

Which Artificial Intelligence tools is most used?

Today most commonly used Artificial Intelligence tools are TensorFlow, PyTorch, CNTK, Caffe, Apache MXNet, Keras, OpenNN, AutoML, and H2O.ai. Each tool is used for different purposes, and choosing the right one depends on the task you are trying to accomplish. For example, TensorFlow is one of the most popular tools for deep learning, while AutoML… Continue reading Which Artificial Intelligence tools is most used?

Published
Categorized as Code

Norwegian conversational AI platform

Boost.ai is an end-to-end conversational AI platform that enables organizations to quickly create, deploy, and manage virtual assistants for their customers. The platform makes use of natural language processing (NLP) and natural language understanding (NLU) to understand customer queries and respond accurately. It also uses self-learning AI to reduce development time and enhance customer communication.… Continue reading Norwegian conversational AI platform

Published
Categorized as Code

Using cgroups in Linux

Cgroups (abbreviated from control groups) is a Linux kernel feature that limits, accounts for, and isolates the resource usage of a collection of processes. Cgroups allow you to allocate resources — such as CPU time, system memory, network bandwidth, or combinations of these resources — among user-defined groups of processes. In order to use cgroups… Continue reading Using cgroups in Linux

Published
Categorized as Linux

New Linux kernel 6.0

The latest Linux kernel is 6.0 and it brings an assortment of performance improvements, new hardware support, security fixes, and the usual grab-bag of file-system tweaks. This includes support for Intel’s fourth generation Xeon server chips “Sapphire Rapids”, and their 13th generation “Raptor Lake” core chips. AMD provides a kernel graphics driver for their RDNA… Continue reading New Linux kernel 6.0

Published
Categorized as Linux