On one hand, they've eliminated the boilerplate I've hated for years. No more googling obscure syntax or writing the same utility functions for the nth time. There's a real joy in focusing purely on the creative aspects again.
But there's a catch. My role has shifted from writing code to managing the AI. It's like being the manager of a brilliant intern with zero memory. My day is now this constant cycle:
1. Crafting the perfect context window to prevent hallucinations 2. Engineering the right prompt 3. Context switching while waiting for responses 4. Painstakingly reviewing the output for subtle but critical errors
So has it killed my interest in programming? Partially. The craftsman's satisfaction of writing code has diminished. But it's sparked a new obsession: building better tooling. How do we reduce this cognitive load? How do we make AI-assisted development more structured and less chaotic?
I'm wondering if others feel the same - has your passion just moved up the abstraction stack like mine has?
`raw_anon_1111` nailed it with the context rot reference. After working with LLMs daily for the past year, I've found that garbage in = garbage out, consistently. It's like working with that brilliant junior dev who can't see the big picture through all the implementation details.
You wouldn't dump your entire git history into a code review, would you? So why would you feed it to an LLM? `ManlyBread`'s "poison the context" is exactly right. Every token spent on explaining dead ends or reverted commits is a token wasted.
The solution isn't more data - it's better data. What we need are tools that create concise, high-signal context packages. Architecture diagrams, clean code, and clear requirements. Not the messy sausage-making that got us there.
This isn't just theory - I cut API costs by 40% when I started curating prompts instead of just dumping everything into context. The attention window is precious - use it wisely.