Programming with LLMs is both promising and frustrating. While these AI assistants can help with coding and debugging, they often waste time too. Y...
For further actions, you may consider blocking this person and/or reporting abuse
This is a fantastic, hype-free curation of real-world LLM use cases by experienced engineers. The 'second opinion' and 'throwaway debugging scripts' techniques are especially relatable—I've found them useful for quickly validating ideas or narrowing down root causes. Also love the emphasis on documenting prompts—something that’s often overlooked but essential for building repeatable workflows. Thanks for sharing these insights; looking forward to experimenting more intentionally with some of these approaches!
Another good one...
The Copilot Delusion
Thanks. I'll check this out.
Love the real talk here, way too many folks hype this stuff up but using it day to day is a whole different story.
Thanks!
Yes, there's so much hype and FEAR. One of my worries is relying too much on it that I lose my ability to think of good/better solutions.
@pmbanugo
Great job my dude!! Loved it!
Love this set of articles! Documenting my best prompts has saved me more times than I'd like to admit.
Have you found any specific format or tool that makes prompt tracking easier?
No. I'm in an exploratory phase, so I just have them stored lcaolly in the project folder. The ones I want to keep long term, I commit to source control.
Good job!
Pair programming with LLM = Vibe Coding
I think they're different, at least in approach and use.