If I wanted a pyramid, I'd want to build it out of stone blocks and be sure that each block is actually stone. I wouldn't want to get halfway and find out that they were actually fragile.

Trusted engineers (of open source projects) can deliver me stone, both the authors and the community (often >100,000 devs) have checked that a specific block is stone and can bear the load.

AI is proven to output all sorts of random stuff. Sometimes a pebble, sometimes foam. It almost always looks like stone to most analysis. However as soon as it's load bearing it's likely to crumble.

Agentic agents have a habit of rebuilding the pyramid and randomly replacing stone blocks with "something else" but we don't know what just yet.