This is days old news now. All discussion, including about the accidental airing/Global TV Canada app etc was merged into that thread from other submissions.
you seem to be entirely missing the point, you are in a frame expecting posts to conform to a ridgid set of definitions, this post has a purpose outside of that frame, as a little bird might tell you.
"You might be the only one expecting a reliable 'AI' agent period."
That is a defeatist take.
Just because the driver (the LLM) is unpredictable doesn't mean the car (the infrastructure) should have loose wheels.
We accept that models are probabilistic. We shouldn't accept that our databases are.
If the "brain" is fuzzy, the "notebook" it reads from shouldn't be rewriting itself based on which CPU it's running on. Adding system-level drift to model level hallucinations is just bad engineering.
If we ever want to graduate from "Chatbot Toys" to "Agentic Systems," we have to lock down the variables we actually control. The storage layer is one of them.
> All my own savings are gone too. (My mother was scammed into borrowing a lot of money and sending it to the scammers, and now it is my responsibility.)
Sorry to hear of your misfortune, but I am wondering why you didn't spot the scam before lending money to feed it.
Buffalo River Aviation’s CEO clarifies that “reports of pilot incapacitation are incorrect and result solely from the Garmin emergency system’s automated communication and reporting functions.”
reply