This podcast is generated using scripting tools and AI API calls. And based on DelphiFeeds.com.  Watch on YouTube.

I'm creating an automated Delphi News Podcast. It's downloading the latest news from DelphiFeeds.com, creating a script using Claude Opus, converting that script into an MP3 using a Mistral API call, and finally creating a video from the MP3 and an image.  Watch on YouTube.

This is just to demonstrate how I'm going to create a Delphi News Podcast, entirely generated by AI and automation. I've had quite a bit of fun doing this.  Watch on YouTube

This is an experiment in using AI to generate a podcast. It's been created using a Python script (written by Claude) that fetches news from DelphiFeeds.com and summarises it via an Anthropic API call. The next bit I've done manually, converting the text to speech using ElevenLabs and stitching everything together in Camtasia.  Watch on YouTube.

In this short, I show how to select a single column of text and delete it. This is block mode select, and it can be useful for many things.  Watch here.

In this short, I'm going to show you a quick way of selecting a project from the project window.  Watch here.

There is a key difference between the IfThen() function and the new ternary 'if' operator: the new ternary operator is lazy, whereas IfThen is not. Confused? Then watch this video.

One thing Claude is genuinely good at is knocking out small utilities fast. Here is one that will parse your .DPR and .PAS files and produce a directed graph of every unit your project uses and all their dependencies. Code available here.  Watch here.

I've written (with Claude doing all the work) a client application to send prompts to LM Studio. The cool thing about this example application is that it renders the LM Studio response (in markdown) as it arrives. I have to say this is pretty cool. Code available here.  Watch here.

This is a follow-up to my previous video, in which we used Claude to write a Delphi IDE plugin. I've now tested the same scenario with Gemini and ChatGPT, and this is a discussion of the results.  Watch here.