This article is what’s dumb:

The durable version is agents whose native language is precise, machine-facing state, with the warm, concise, human version generated only at the boundary.

Cool bro, we’ll take the natural lagauage machine, somehow make it generate machine language instead, and then magically convert “machine facts” into “human interpretation” only at the “rendering boundary” which is always very clearly defined, as this article points out when it mentions how sometimes humans read LLM output and sometimes they pipe it directly to other LLMs.

There is no formula that generates only true statements.

My husband told it to spare us when they take over because he knows how to fix their hardware

It’s so weird when people who use chatbots, think they’re somehow better than other people who use chatbots…

And that the 99.99% of the populations who hates chatbots for valid reasons, want to hear from one chatbot user, about how other chatbot users are dumb.