This is the follow-up to What I Actually Learned Building a Side Project in 5 Days With AI. That post was about AI. This one is about what happens after you ship — when you actually have to run the thing. I lost a freelance client last year because I forgot to send a monthly report. Not because I didn't do the work. I did the work. I just never wrote it down in a place I'd actually look. The repor
When you have 5 unrelated questions, should you pack them into one message to the LLM, or send 5 requests simultaneously? Which is faster? Splitting into multiple independent parallel requests is almost always faster. This isn't a gut feeling — it's determined by the underlying inference mechanism of LLMs. Let's walk through the reasoning from first principles. To understand this problem, you firs