A particularly pronounced version of this can often be seen by letting 2 agents review and code in a loop. One agent will find some problems with the code, the other agent will address the review by adding more code.
A good human developer might see that the better way to address the review is to backtrack and pick a different approach. The ai agents seem more prone to getting stuck down bad branches of the decision tree.
Code reviews should be done by someone other than the author though, so the only thing that changes with ai generated code in that respect is the amount of it
In relation to the client (AI Agent), the MCP server is serving resources like tools, but in relation to your platform that hosts the API those tools call, it is a client.
I share your frustration on services that won’t let you automate them, but to me that’s precisely what generative AI will let you do. You don’t need an API at the family doctors to have AI automate it for you. It just rings them up and sorts it out at your command. AI is like obtaining an API to anything
Lowering the speed limit where there are sidewalks next to cars driving seems to work well in Europe. But that also requires policing of those speed limits so they are not considered mere suggestions by drivers.
An excellent write up on this great game! One particularly striking element of Curse to me is the soundtrack. Michael Lands compositions for the series is absolutely perfect in this high fidelity form. The familiar themes from the earlier games take on a whole new dimension and the music has its own narrative which perfectly complements the visuals and gameplay. A masterpiece in its own right. I still find myself loading it up on YouTube and playing it in the background while working or doing house chores.