Back in the very early days you would have used script/plugin install (svn url)

Here's one of my mirror repositories migrated from SVN into git. https://github.com/jaggederest/acts_as_voteable

As time has gone on Rails has gotten better about this, but it still means that "your rails" and "my rails" are different enough that AI could easily get confused.

As you say, the other aspect is the intense dynamism which works against AI, which again prefers to have everything explicit and reasonable about from the text.

So I ended up going back to Javascript after a brief 12 year digression into Ruby. I still love Ruby but it's just not the right language for the current environment and team structures - typescript is "worse is better" in the right ways that it's a much better choice for both frontend/backend being the same and better type systems.

You see this recently over the last couple years in tech where everyone is "an AI company" even when they make something totally unrelated - same impulse, different industry.

Seems deece

That's why it's a motor, like in dishwashers, not a thermostat like in e.g. greenhouse windows or radiators.

It doesn't need to be persistent, but without some way to create a state that is different than ambient, it's not a motor.

Thermostatic valves are ambient at both sides - they expand and contract naturally with the existing temperature, so they are not motors per se, because there's no actuation beyond the temperature.

I've been using languages with stronger type systems and that's also a huge boon.

I once worked at a very large company, and one of my coworkers was like "eh, I'm not going to do any of this work, because I don't have to", and that was a clear indicator that the problem wasn't (just) with the system, but with him individually.

You need two pieces:

a) prompts, that tell the agents what to do and how to do it (and ideally, the why, where, etc, the full picture) - that's the positive half, that drives behavior the way you want it.

b) deterministic tooling that prevents negative outcomes, like linters, compilers, static analysis, fuzzing, testing, the more the better. This side should either be firewalled off from the AI or very carefully watched so that it doesn't drift.

The part that you put in the deterministic side is the "never do x" stuff - I have lint for long comments (which AI hits every single time it commits), all my dev scripts are in typescript, precommit hooks, massive CI, and I lint even for things like redirecting error to standard out, tiny stuff, and also e.g. static migration analysis so the AI never ships an exclusive full table lock in a migration, for example.

Gasoline, when it goes bad, goes bad from top to bottom and is not recoverable through e.g. a centrifuge like https://www.youtube.com/watch?v=x4Fdu3e4gYw