I really like this idea. Gonna need an "Awesome Axe" page that collects agents.
One idea I'm thinking of is, after an agent has been in use for a while, and built up and understanding of the task, would be something like, "Write a Python script to replace this agent."
I could imagine this would work with agents that are processing log files or other semi-structured data for example.
“For months, callers to the Washington state Department of Licensing who have requested automated service in Spanish have instead heard an AI voice speaking English in a strong Spanish accent.”
For some reason this reminds me strongly of an old play-by-email game called C++Robots[1]. I loved the idea, but the timeslice limitation[2] I found too annoying.
I had youthful dreams of re-implementing something similar that would run on the Java Virtual Machine, where you could run the submitted robots via the debugger interface so you could keep "real-time" in the game environment more authentic. Ideas are cheap, follow-through is hard.
I've noticed a habit of late of people accusing a comment of being LLM generated if they disagree with it. It was getting quite tiresome a few weeks ago but seems to have died down.
I suppose it is possible that they are actually LLMs making the accusations? :-)
(I'm one of those weirdos that try to use proper grammar and complete sentences in text messages and instant messages.)
How have you been tracking down all the bits and pieces from your operating system that the agent still needs to do what it needs to? I'm working with Java projects and Gradle builds and the list of stuff is getting crazy.
The biggest hold-back for me is that, here in Australia, Google Wallet (aka Google Pay) is the only way you can do tap credit card payments that I know of. Can't with Paypal. Not with any banking apps that I know of.
It's just so damned convenient. And the recording of transactions on the phone saves me having to collect paper receipts.
It's also absolute awesome how every person's brain works the same way. It makes it some much more convenient that what works for one person works for every person.
One idea I'm thinking of is, after an agent has been in use for a while, and built up and understanding of the task, would be something like, "Write a Python script to replace this agent."
I could imagine this would work with agents that are processing log files or other semi-structured data for example.
reply