A common topic at Reddy lately has been how far can we go with LLM automation. Inference is cheap, so our primary target is getting reliable output without manual review. I want to address what makes this hard and my model for reasoning about it. Note: Most of these processes don’t need latency or cost…

Six months ago I left the corporate world at Ball Aerospace to found an AI startup with Adam, who I’d met on Twitter only briefly before. We hadn’t even met in person, yet I left one of the most stable 6-figure tech jobs where I had no complaints. It was a hard decision because I…

You probably shouldn’t read this if you made any new years resolutions, but if you didn’t, give yourself a pat on the back. I never commit to anything on Jan 1, and for good reason. Everyone has an idealistic view of their goal – it’s impossible to know in advance what it’ll feel like when…

Note that this was originally posted for a tweet while I was still relatively early in our development stage. I’ve single-handedly shipped an app to production and this has worked great, but time will tell if it holds up as our development team and application size grows. I’ll be coming back to this article to…

Why does it take so long to launch products? Building working MVPs in a matter of days doesn’t have to be a dream, and no, you don’t have to be the world’s fastest developer. You will quickly become a well-paid developer though. I learned web dev a year ago and already make far more $…

Now… If you’re here from Twitter, you probably asking: What’s this graph about? We’ll get there, hang with me for some context. Disclaimer First, let’s be clear. This isn’t my idea, and this isn’t about me. I built something cool last night, but other’s have done exceedingly more in this space than I can even…