Looks interesting, but I feel that as models get better and better, the need to have 'personas' for each agent is actually a drawback compared to having a well-defined starting plan and objectives, because more 'intelligent' models will just figure out a more efficient way to do what they need to do.
I'll wait for the follow up posts "setting up reasonable budgets for ai-native organization" and "validating (benchmarks/evals) that your ai-native setup has any benefit over a simplistic ai-assisted org"
I'm happy to see I'm not the only one using mythological creatures as agents :)
They are currently only Simulacrums but there is no telling where the open-ended loop will end.
"Juan is responsible for the tech" first of all, one of these cute names is not like the others. but more importantly... what on earth does "the tech" refer to here?
Their E&O insurance policy premium must be triple that of any regularly staffed organization…that is if they have the guts and brains to get said policy. Doubtful.
<vomitting>
How about an I-native org?
if you are still not clear about the definition of Ai slop, it is right here :)
ai generated slop
Hardliner pro-AI slopaganda. Recently, the Internet is like living in a communist country where you just cannot escape the hourly propaganda.