Comment by iExploder

After 12+ years of hardcore c/c++ in embedded, I'm having a blast with Claude...

my productivity definitely improved.. especially with tasks that I would consider boring or tedious to hand code due to repetition (I have coded this at company X and now Im doing N-th variant of it again at company Y from scratch...) claude will mostly one-shot these things with proper prompt and constraints.

I think software engineering has changed, the new paradigm is creating proper fixtures for agents to run in (like environment, code execution and bench/unit test access) and defining specs, inputs, outputs and constraints of the problem, then let Claude iterate on it and sip on coffee.

I find that some "taste" in software and understanding complex systems is needed for "agentic coding" to be useful. I like to constrain the system (code and problem wise) to decrease the potential search space, otherwise the things tend to fall apart after a few prompts.

One negative I'm seeing is people generate huge PRs with endless PR descriptions, just cos its easy... I believe less is more with these tools and effort should be made to keep the changes minimal and filter out of the excessive noise from code and docs... however I understand the incentive of LLM providers is to maximize amount of changes and complexity of the codebases (more tokens more $$ to extract :) so this will most likely be a never-ending battle