The landscape of artificial intelligence (AI) is undergoing a notable transformation, shifting from the pursuit of ever-larger language models (LLMs) to the development of smaller, more efficient models. This shift, driven by technological advancements and practical considerations, is redefining how AI systems are built, deployed, and utilized across various sectors. The Shift in AI Model...
Author: Martin Treiber
Understanding Tokens in AI
In the realm of Artificial Intelligence (AI), particularly in the context of Large Language Models (LLMs), tokens are the fundamental units of language that enable machines to comprehend and generate human-like text. This article delves into the world of tokens, exploring their definition, history, types, and significance in the AI landscape. What are Tokens? In...
Embeddings: The Secret Sauce in AI’s Data Cuisine
In the world of artificial intelligence (AI), data is the main ingredient. But just like raw ingredients need preparation before they become a delicious meal, data must be transformed into a palatable format for AI systems, particularly large language models (LLMs), to "digest." This is where embeddings enter the kitchen, serving as the secret sauce...
What are Jupyter Notebooks?
Welcome to the exciting world of Jupyter Notebooks! Whether you’re a seasoned data scientist or a curious beginner, Jupyter Notebooks offer a versatile, interactive environment for developing and sharing code. In this post, we’ll explore what makes Jupyter Notebooks a powerful tool for data analysis, machine learning, and beyond, along with practical examples to get...
AI and the Future of Software Development
Imagine standing on a podium, baton in hand, ready to conduct a symphony of code. This is the future of software development, where developers act more like orchestra conductors than solitary coders. As someone working with LLMs, I’ve witnessed firsthand the rapid advancements that have transformed our capabilities. These changes bring excitement and anxiety, hope...
Custom GPTs vs Assistants
In today’s rapidly evolving tech landscape, AI-driven solutions are becoming integral to enhancing user experiences and automating tasks. Among these solutions, OpenAI offers two powerful tools: Custom GPTs and Assistants. Both cater to different needs and skill levels, making it essential to understand their distinctions and applications. In this blog post, we will compare the...
Rabbit R1: A Glimpse Into the Future of AI Gadgets?
The Rabbit R1, the latest entrant in the AI gadget market, has stirred quite a buzz, not only for its vibrant, eye-catching design but also for its ambitious blend of AI capabilities. Initial reviews by Mashable, Engadget, The Verge, ZDNet, The Atlantic point out, this device promises to revolutionize daily tasks with a simple voice...
Closing the Automation Gap
In the evolving landscape of digital automation, a significant gap persists between the potential of automation technologies and their application in real-world scenarios. Modern LLMs have virtually no control over legacy apps on computers, smartphones, respectively: they cannot move a cursor on a desktop, cannot input text into fields or start apps. However, there has...
Every Day Prompt Engineering Part 7: Data Analysis
A somewhat overlooked feature of ChatGPT is its ability to analyse data. ChatGPT is capable to read files, analyze them and provide visualizations, files and analysis. In this blog post, we will take a look at how to use ChatGPT for data analysis. To demonstrate the power of advanced data analysis, we will use data...
Is AI the end of bullshit jobs?
David Graeber's essay, "On the Phenomenon of Bullshit Jobs," published in STRIKE! Magazine, provides a critical examination of the modern workforce and the proliferation of what he terms "bullshit jobs." These are roles that the individuals occupying them perceive as meaningless and unnecessary, contributing little to nothing to the betterment of society. Graeber explores the...
