I still do a fair bit of z80 programming for myself, and I'm very familiar with the Spectrum so this was a nice article to see, but it's a bit underwhelming how well this seemed to go.
It’s still impressive, but it’s basically advanced autocomplete. You still have to read and check every line and make sure it is doing what you expect it to do.
but yes, indeed you still need to watch it like a hawk when using it outside of a tight eval loop (ie. make all | make property-tests) and/or implement some other form eval loop on the original /spec generation.
To me it looks like your comparison to Tesla FSD is much more apt than you realize. If you want the "magic" to work you have to trust it, and accept that it will run you over the cliff the first chance it gets.
If you're a true fan you'll then head to hackernews to explain that "if only i had stopped it from running me over the cliff, the technology would have been amazing".