-
Read more...
-
Listen! I'm tired of typing (stream 390)
Summary
We spent the day wrestling with AI dictation services and PipeWire audio drivers, proving that tech support is harder than it looks. Marcel and McNet absolutely crushed the drop game, leaving poor Dev and me in the dust. Thanks for tuning in, and I hope you have a fantastic weekend
đź“ş - Twitch archive - stream no. 390
Replay
Read more...
-
Working on... stuff (stream 389)
Summary
Kicked off the stream half-blind after scratching my eye, wrangled Twitch quirks, and still demoed my “video-to-blog” Python app, complete with AI-written posts and frame grabs. Chatted about adding Keycloak to my GPX project, and warned off crypto spammers while cheering on all the digital friends raining down. Wrapped up dreaming about N8N nodes, conferences, and maybe actually finishing a full two-hour stream someday.
đź“ş - Twitch archive - stream no. 389
Replay
Read more...
-
Working on co-author, an AI tool to help creating content (stream 387)
Summary
In this stream, I experimented live with AI-assisted “vibe coding,” trying to one-shot a .NET Aspire app that generates blog posts from videos and extracts keyframes automatically. I compared tools like OpenCode and Copilot, talked through architecture choices (containers, FFmpeg, UI), and debugged issues in real time with the chat. In the end, I realized a fully one-shot approach wasn’t ideal for a project this complex and decided to pivot back to a more iterative, pair-programming style when using smaller (less performant models).
đź“ş - Twitch archive - stream no. 387
Replay
Read more...
-
Building a tool to help me creating content, and yes it uses AI... obviously (stream 386)
Summary
Today we kicked things off by exploring GitKraken’s awesome new 11.8 release with features like ARM support and AI branch explanations—huge thanks to the team for always delivering such polished tools! But the real fun started when we brainstormed our new project “co-author,” a tool designed to help you write blog posts from video files using AI vision APIs and Python, all containerized and ready to go. We mapped out the core features like extracting key moments from videos, managing them in a library, and handling both video URLs and local files—I’m super excited to start building this one out!
đź“ş - Twitch archive - stream no. 386
Replay
Read more...
subscribe via RSS