Author: OSKAR DUDYCZ

The more detailed you make your prompts, the better Claude Code performs. But to get it to work correctly, you need specifications so detailed that you’ve almost done the implementation.

You’re not necessarily saving time - you’re programming in Markdown instead of code. … So, to be effective, you need to behave just like Gabriel. You need to watch Claude plotting stuff in the console. As one moment it generates sensible code, then completely loses the plot the next. … Speaking about junior devs. Many people claim that working with LLM is like working with a junior. I think that’s disrespectful and just plain wrong. Junior devs don’t have enough knowledge yet, but they learn, you can teach them, mentor them, and they will get better. They can also reason and react based on what they’re doing; they’re not just code outputters. LLMs won’t learn, as they don’t have memory; they just have context, which they happen to lose quickly and randomly.

I think this is a great take. If AI agents WERE really like Jrs they would learn and grow. no amount of AGENTS.md or README.md have made an impact imo. and yes sure you can program asynchronous but you’re constantly check in on did it go awry. And don’t even get me started on yolo mode or run all commands mode.

The future is wild.

_{Quote Citation: OSKAR DUDYCZ, “Requiem for a 10x Engineer Dream - by Oskar Dudycz”, AUG 11, 2025, https://www.architecture-weekly.com/p/requiem-for-a-10x-engineer-dream}