Ironically now it seems that the companies that make these companies are the only ones to profit from slop software.
There is no other reason for this to happen other than that the people responsible didn’t take care to check the code they are pushing. Which should be a signal in itself but I suppose it doesn’t matter if it is “good enough.”
In my experience I could never leave the agent off and go on its own. That is while I also use them extensively for all my work.
I still cannot wrap my head around people who spawn tens and sometimes thousands of agents hoping for the best and then saying how little token limits are. The only way that is possible is when your work is superficial and you have no idea what you are doing (or it’s a hobby project).
It is not even laziness at this point. There is so many conflicting and convoluted config formats and utilities (especially in the javascript ecosystem) that if you made it your mission to know it all, you would literally spend your whole life on it.
Yeah the only issue is that it is a major vendor lock-in + hazy perspective, so it is essentially unfit for any "serious" processes (read: mission critical / where you have to invest time and effort). I guess you could simply copy-paste the prompt from there in case of emergency. That is, if they allow you to.
Other than that it is a really neat utility and saves some time. However, I feel like there can be OpenClaw moment for this as well. Somebody simply needs to create an open-source version that supports all of the agents and models.
"That sparked an idea: why use an industry-proven solution when you could just build your own patient management system?" lol
I wonder if it is an actual dunning kruger effect at play here (confidence issue) or the lack of critical thinking. The first one could be excused somewhat, but I am afraid it is more of the second one