Let me take a swipe at it: a semantic layer helps express queries and their results in terms the end-consumers will care about / prefer to reason in, instead of whatever extremely correct and efficient atrocities the database nerds came up with.
Did I get that right?
Very unfortunate
If you read through that claude.md, it's a well-organized summary of the project, touching on design, architecture, enumerating the functionality implemented so far, future goals, and more. It makes for a pretty great onboarding document for collaborators, tbh.
Have jetpack, will fly.
Sure, let's hear the counter-example of the noble startup, taking massive risks to build The Coolest Thing. Like the enthusiastic wiggly sperms, one in a million succeeds -- and the consequences of initial success are to grow mediocre over time.
LinkedIn is marketing slop, aimed at the lowest common denominator, because that's the most numerous denomination of the walking wallet. Of course it is saturated with family friendly, inoffensive, endless streams of softcore corporate propaganda.
I've been leaning hard on the code-gen crutch, don't get me wrong, and it's a force multiplier some of the time. I'm not even doing anything that out there, but it keeps stumbling over its shoelaces all the time.
Or, you know, send your own AI agent into the interview.
We've had something close to a drought this summer -- unseasonally long periods without rain. You can see the young trees on the streets and trees in the middle of large parks suffer from it - wilted leaves and leaves dropping earlier than usual. BUT, large old trees seem to be thriving - full canopies, lush, firm leaves.
I've been suspecting the big street trees do so well because they benefit from the dilapidated state of our water delivery infra. It's nice to read of a study that confirms my amateur observations and musings.