One question missing from the list, and it’s the first one I tend to ask… do we really need this? I’m not sure I’ve ever seen an agent pushing back on a request.
You can tweak them to do so. I personally tweak mine to act like a disappointed stack exchange veteran.
I personally recommend, but I understand many people do not want to be pushed back by something they see as little more than a servant.
This setup does work to also have agents argue with each other. That can be very interesting, though you have to set them up to be very skeptical. Otherwise they will tend to read another agents assertion as authoritative off the bat.
I am convinced much of the harness/prompt engineering we are doing now will also be automated away. Within 5 years the best practices for the most popular use cases will have been found, automated and fully baked in.
The only thing I see happening is agreements between the biggest players and the content brokers, squeezing out others who’d like to enter. At least just now anyone can theoretically scrape the web for useful info.
The bigger problem I see coming down the line, given the current business model for the internet, is what happens when investors need a return. When the LLM only provides one “correct” answer, the only way to make money from advertisers is to influence that answer. At least just now we are presented with information which we evaluate ourselves, though even this is subject to manipulation.
