The “catastrophe scenario” of AI in the software engineering job market has gained quite a lot of popularity, with people pointing out that current models already “do a better job” (what does that even mean?) than many professional programmers. I’m not sure I completely buy into this.

I’ve been playing with dalle-mini the last few weeks. Part of what makes it fun to play with are the bizarre and obtuse outputs. They reached that sweet spot between laughably bad and frighteningly perfect: they’re good enough to be understood and enjoyed, basically.

I think that incompleteness is part of what makes it so amusing to toy with these things, and conversely what will make future versions much less fun.

TLDR We launched Podlettr - go check it out!

For nearly two years, me and my good friend Sérgio Fontes, an accomplished product designer, have been working on Podlettr - a great way to quickly catch up with your favourite podcasts. As the name implies, Podlettr is a letter from your podcasts. Reading is faster than listening, and with some AI magic, we convert hours worth of podcasts into beautiful, easy-to-read weekly newsletters.

We both have demanding full-time jobs and family duties, so we had to be pragmatic with the frameworks and architecture choices we made. Rails was my obvious framework of choice. Within weeks of the initial idea, we had a working prototype.