I think the answer is yes, we are getting lazy by delegating a lot of work to LLMs. The offloading thinking seems to help because we can get answers faster, but we aren’t using our brains as much. In the long run it will be a bad thing
I like the idea of saving the work done into files - helps to prevent the llm from redoing the same work. Maybe one day instead of code in a repo it will just be a list of prompts.
Usually if you’re a manager, your job IS the meetings - or a large portion of it. You’re responsible for a remit and the performance of people inside the group and what is delivered. I think it’s unlikely that can be done of high quality without meetings, but ymmv
+1 I did the same a few years back. It’s fine most of the time. Their AI assist is ok as well. No complaints here, can always fallback to google if the results aren’t good enough
Slightly different but related topic - for people who work with people vibe coding, what is the easiest way to allow that for non tech users (and reducing risk)? AWS or something like vercel? Coolify?
It’s worrying to me that nobody really knows how LLMs work. We create prompts with or without certain words and hope it works. That’s my perspective anyway