Writing blog posts comes almost natural for AIs. After we went through a few email scenarios in the last installation of our series, we’ll focus on how to use AIs for writing blogs. Why blogs? Blogs are an invaluable asset for businesses for several reasons. Firstly, they significantly enhance a company's online visibility. Search engines,...
Category: Tipp
Everyday Prompt Engineering Part One: Emails
After we’ve discussed the basic elements of prompts, it’s time to apply them for everyday tasks like writing emails, drafting presentations, writing blog posts or making web pages. The possibilities are more or less endless. Today, we will focus on emails. Emails Emails are the backbone of modern business communication. Despite claims of their obsolescence,...
Is GPT-4 getting lazy?
In recent weeks, users of ChatGPT-4 have reported a notable decline in the AI's performance, observing a tendency to avoid certain tasks or deliver overly simplified answers. Put differently: it appears that ChatGPT-4 became lazy. OpenAI has acknowledged the problem, though the exact cause remains uncertain. This phenomenon has led to the speculative "winter break...
Key Elements for Effective Prompt Engineering
As we delve deeper into the fascinating world of prompt engineering, you'll start to recognize certain key elements that form the backbone of an effective prompt. Think of a prompt as a conversation starter with an AI, where you guide the AI to understand not just what you want, but how you want it to...
How to prevent hacking your custom GPTs
When OpenAI introduced custom GPTs and a future (now delayed to 2024) GPTs store many (like myself) immediately started to work on their own GPT. It’s super simple to create it’s a new and exiting field and most importantly it’s simply fun to experiment with. However, not long after the first CustomGPTs were published, it...
Introduction to prompt engineering
Welcome to the fascinating world of Prompt Engineering, a key to unlocking the full potential of artificial intelligence (AI) interactions. In this digital era, AI models have become incredibly adept at understanding and responding to human language. However, the effectiveness of these interactions largely hinges on how we communicate with these models – this is...
How to train LLMs with knowledge distillation
Knowledge distillation is an area of research into more efficient Transformers which trains small models (students) by encouraging them to reproduce the outputs of large models (teachers). This is a technique which initially gained popularity on classification tasks in computer vision, but has been successfully applied in several domains, including LLMs. If you start from...
Goodbye Siri – Embracing ChatGPT as Your New Voice Assistant
With news that OpenAI’s ChatGPT Voice feature is now available to all free users, you can ditch Siri as your main voice assistant on your iPhone. Here's how you do can do it. iPhone 15 Pro and Pro Max The latest iPhones from Apple, the 15 Pro and Pro Max, support the ability to configure...
Mastering ChatGPT with structured Prompting
ChatGPT's ability to churn out text has garnered attention, but achieving high-quality output often seems elusive. The bridge between mundane and magnificent lies in the way one prompts ChatGPT. The following approach to structured prompting aims to turn the keys in the right locks, unlocking a level of finesse in content generation. 1. Persona Instruction:...
What Makes a Great Resume in 2022?
Whether you were part of the Great Recession, the Great Retention, or somewhere in between, are you looking to upgrade your resume in 2022? How does your resume stack up against the competition in today’s job market? The truth is, there are good resumes and there are great resumes. The quality of your resume can...
