> Personally, I've found even the latest batch of agents fairly poor at embedded systems
I mean even simple crud web apps where the data models are more complex, and where the same data has multiple structures, the LLMs get confused after the second data transformation (at the most).
E.g. You take in data with field created_at, store it as created_on, and send it out to another system as last_modified.
No, it is not it. The idea is that the living module or RV is still occupied during the travel unlike the motorail, where passengers are traveling in separate passenger cars. Car shuttle trains where passengers stay inside the vehicle also do not offer connection of utilities to RV. And my idea goes further where living module is disconnected from engine/wheels platform when loaded on the train (if the design is standardized similarly to containers, you can get new one at the destination, so the train carries less weight).
Weight is not really an issue for trains, RVs / cars weigh absolutely nothing in comparison to even just a rail car.
For safety reasons you can't really have people sit in their cars on the train. The Eurostar etc. has extensive fire systems et. al. to make it possible.
As with most things, I think there's multiple things. US home also tend to be larger, meaning the hot water line is longer from the tank to the shower. Most americans I know tend to leve the shower running before they get in so it "warms up". I've never been in a European shower that's required that.
Not just the bigger homes, from what I can tell in US home construction the length of the hot water pipe isn't a consideration at all, while it is a common consideration in European homes. In Europe (vast overgeneralization incoming) it's not unusual to have a boiler or a tankless water heater directly in the bathroom to keep the line short, and then have the kitchen close by. Having multiple water heaters per home is also completely normal and a common solution if the kitchen is too far from the bathroom or multiple bathrooms are far from each other. In the US the norm seems to be to just stick a big boiler in the basement or somewhere else out of the way, then run hot water lines everywhere. Maybe in part due to the added effort of running 220V lines in a 110V country
Not really just lawns, but irrigation specifically. I know a lot of people in my country that have detached houses with lawns. I know of no one that owns a sprinkler system. Dry years the lawn just goes a bit brown and no-one cares.
Everyone has a hose, they wash their car and water their flowers by hand.
This does also tie in directly with tickets and the overall workflow the team has. I find this to have a huge effect on how managable PRs are. I feel the majority of devs are quite oblivious to the code they produce, they simply keep coding untill they fill the acceptence criteria. No matter if the result is 200 lines in 1 file, or 1 000 lines in 30 files.
It depends on how you use it. The "vibe-coding" approach where you give the agen naive propmts like "make new endpoint" often don't work and fail.
When you break the problem of "create new endpoint" down into its sub-components (Which you can do with the agent) and then work on one part at a time, with a new session for each part, you generally do have more success.
The more boilerplate-y the part is, the better it is. I have not really found one model that can yet reliably one-shot things in real life projects, but they do get quie close.
For many tasks, the models are slower than what I am, but IMO at this point they are helpful and definitely should be part of the toolset involved.
> The more boilerplate-y the part is, the better it is. I have not really found one model that can yet reliably one-shot things in real life projects, but they do get quie close.
This definitely feels right from my experience. Small tasks that are present in the training data = good output with little effort.
Infra tasks (something that isn't in the training data as often) = sad times and lots of spelunking (to be fair Gemini has done a good job for me eventually, even though it told me to nuke my database (which sadly, was a good solution)).
I mean even simple crud web apps where the data models are more complex, and where the same data has multiple structures, the LLMs get confused after the second data transformation (at the most).
E.g. You take in data with field created_at, store it as created_on, and send it out to another system as last_modified.
reply