URLs rot, domains expire. So I don't think the problem went away completely.

Maybe they did?

they didn't get good results

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)).

If it's truly an AGI it would just ask to talk to your boss as the whole project is a drain on humanity and your own soul.

Look into ticker tape, and dot matrix printing, this is how early computer displays worked.

The proliferation of roundabouts over stoplights in Espoo has massively improved traffic in many many areas since I was a kid and it was all stoplights.

Weekdays during office hours, yeah. Sundays street parking is mostly free.

This stuff gets unbearable very fast. We have custom types for geometries at my work. We also use a bunch of JS libraries for e.g. coordinate conversions. They output as [number, number, number], whereas our internal type are number[].

nickslaughter02 accounts only comments seem to be slandering the EU.

It’s almost as if their account was created for this purpose. I sometimes wish HN had the lobsters invitation model.

Yes, let's silence opinions we don't like. Just like **.

I wonder why this comment is at the top of the HN post.

Over the years I've seen a lot of missinformation on this topic that follows pretty much this exact train of thought. Why would countries join the EU and the Euro if it didn't benefit them?

The baltics have all grown massively since the 90s when they became independent, and even though they all were on nice trajectories they still all decided to join the EU and the Euro.

Bringing up the UK as some model for all other "small" european countrie sounds odd. The UK joined the EEC specifically because it had slower economic growth than the other large EU countries.

The UK, and specifically the city of london, with its huge international financial pull has a very different place in the global economy than Bulgaria...

> Why would countries join the EU and the Euro if it didn't benefit them?

Joining benefits the country's elites, rather than its general populace -- and it's these elites who decide whether to join.

Bulgaria joining will weaken the Euro, which benefits big, export-oriented economies such as Germany and France. This is how the Euro has always worked: the big economies dilute their trade surpluses at the cost of smaller European countries.

no proofs, just rephrasing what anti-eu propaganda says. also it is nice how people think they are able to dismiss a policy like the euro in 2 sentences thinking they understand it. probably without a phd in economics either.

> Joining benefits the country's elites, rather than its general populace -- and it's these elites who decide whether to join.

That's bullshit. The decision to join is made via referendum.

all the elites like the expats in Spain.