Although the expression “Prompt Engineering” sounds pretentious and a tad bit exaggerated, it’s a kind of interesting area to study and comprehend how it interacts with AI powered chat bots, such as Gemini, Copilot or ChatGPT. The following article is an interesting read on the subject. Click here or on the picture bellow.
Image generated in Copilot, using DALE-3 with the following prompt: “Can you give an image based in the following description, regarding Prompt Engineering, please? ‘Non-Obvious Prompt Engineering'”. I think it could do better if the prompt had been improved. But it wasn’t!
“There are many stumbling blocks on the racetrack to nuclear fusion, the reaction at the core of the sun that combines atoms to make energy: Generating more energy than it takes to power the reactors, developing reactor-proof building materials, keeping the reactor free from impurities, and restraining that fuel within it, to name a few.
Now, researchers from Princeton University and its Princeton Plasma Physics Laboratory have developed an AI model that could solve that last problem. This model predicts, and then figures out how to avoid, plasma becoming unstable and escaping the strong magnetic fields that hold it inside certain donut-shaped reactors” – in Vice’s Motherboard section.
“A photo realistic picture of long shelf over an old but well cared for wooden floor which you can only see a small strech of it. The shelf goes from the floor, up to the ceiling, completely filled with vinyl records, with sleeves of different colours. There is light in the room but you can’t see it’s source. The image should have a squared aspect.”
