Awesome, thank you! This largely matches my own experience, I’ve found it (Claude in my case) most useful in areas where I’m weakest. I haven’t tried this scaffolding-via-comments approach though, it sounds cool.

Any experience with Cursor or other IDEs or agents? Was co-pilot a choice or just kinda a natural default?

Would you mind sharing a bit more about the workflow you’re describing? I’m on a “ask people how they’re using AI to help them dev” kick.

Sounds like you’re using an agent integrated with your IDE, would you be willing to give specifics? And you’re talking about writing some comments that describe some code you haven’t yet written, letting the AI take a stab at writing the code based on your comments, and then working from there? Did I get that right?

Happy for literally any elaboration you feel like giving :)

That graphic in the second link, holy shit

Completely agree! It’s SO much easier to lighten the mood and keep things upbeat and productive in an actual conversation vs. just text-based feedback. For example it makes it easy to throw in self-deprecating anecdotes of your own when discussing mistakes / needed changes, which can really help put juniors at ease. It’s just worlds better in >90% of scenarios.

Completely understand the frustration here. Mistakes happen, even competent people sincerely trying to do a good job can overlook things, etc. But if it’s a pattern of just copying and pasting code without really even trying to understand what it does, that’s a big problem that needs to be addressed. And frankly they should feel embarrassed if it happens more than once or twice.

OTOH, delivering criticism in a way that winds up productive for all involved is difficult at best, and the outcome depends on the junior as much as it does the senior. What good is being right if it ultimately just alienates you from your team? Tough situation for sure, and one of the many reasons it’s so important to hire carefully (which is itself a whole huge can of worms too!).

Can you simply ask them to walk through their submission line by line with you, explaining what it’s doing? If you’ve never asked that before it might come across as a strange request, but if you phrase it well it’s possible this causes them to notice their poor understanding without you ever seeming to point it out.

I like it, very succinct way to get the point across.

That’s the way these things have always gone and probably always will. Retarded, imbecile, idiot, these were all effectively clinical terms (or whatever best approximated clinical practice in their eras) - they didn’t hold an insulting intention initially. People co-opted the terms to make fun of each other, as we do, and so professionals had to shift the clinical vocabulary so they weren’t using commonly hurled insults when discussing patients. And that means new words people can use to make fun of each other, yay! Which of course they did, necessitating another rotation. Pretty hilarious if you ask me.

The most recent example in my own life - my wife is in her mid 30s, and is pregnant - some medical professionals call this a “geriatric pregnancy”! But because some folks are getting offended by that term, they’re starting to use “advanced maternal age pregnancy”. Bit of a mouthful, I think they’ll get to keep that one.

Anyway. Carlin had a great bit on this phenomena, he’s the one who pointed it out to me.

Excellent work, and thank you for sharing. What a win! I’m always heartened to hear about straightforward open source wins against leeches 👍