using AI to build software and how to avoid the race to the average
Using AI to build software can result in a slippery slope towards developing average code.
PLEASE ACCEPT OUR. COOKIE POLICY
I have used Adobe Photoshop and other Adobe software for a while now, but I still feel that I am a complete amateur when using it. However, Adobe have given me access to Adobe Firefly, a Generative AI tool. This enables users, amongst other things, to type in text and have an image created for them. This is particularly interesting for me since, despite years of on and off effort, the results I get using Adobe software is poor.
The easiest way for me to use Generative AI is to use the Firefly website. The tool I used within that site was "text to image". The user simply types in some text and changes some settings such as style (photo, art etc), shape (square, portrait, landscape etc) and the image is generated for them.
After around 5 minutes of using the Firefly website I created an image that I was quite happy with, and was definitely something I could never have created by myself. The text that I finally settled on was "A dark haired young lady looking thoughtful with code coming out of her head and the code is morphing into a sports car".
Adobe are also embedding the same Generative AI technologies throughout their vast array of software products, including Photoshop, and have recently released Beta versions. I installed the Beta version of Photoshop but, as opposed to excellent results I got from the Firefly website, the results were less than impressive. I experimented with using text to image within a Photoshop file but it quickly used up most of the memory (32Gb) on my computer and grinding it to a halt. Also, the file that was created was 7Gb, which is huge.
Using AI to build software can result in a slippery slope towards developing average code.
Using DotNet 8 and Aspire With Azure Container Apps Makes Kubernetes Enabled Apps Incredibly Easy
Moving to a micro-services architecture can sometimes seem daunting due to the amount of technical choices to be made and the amount of planning involved. Often however, the migration can be made in manage-able steps. Here is one classic example.
Fast Endpoints have become very popular with .Net developers recently, but how much faster are they than regular Controller endpoints using .Net 8
GPT4 and other tools have good text summarisation capabilities but only Deep Mind is providing the real breakthroughs.
Managing Infrastructure State can be tricky in the cloud. AZTFY and Terraform can help with management