misja111

Until half a year ago I used to agree with you, but nowadays Claude has gotten so good that I have to admit it's a better programmer than myself. Its coding style is excellent, it follows whatever conventions are used in the codebase, it has excellent suggestions for refactorings and it spots omissions or mistakes in the specifications I give it.

(I'm using mostly Scala as a language in a large microservices environment)

Tell me you're a bad engineer without telling me.

If you don't understand what you are building, chances are you'll take suboptimal decisions or even come up with a solution that completely misses the point.

To properly understand what you are going to build, it's not enough to read specifications from some manager as gospel. You need to ask questions, and challenge the requirements sometimes, to make them your own.

Exactly what I saw as well. Some not so good ones have even stopped using AI at all, arguing it 'just got confused'. Good ones on the other hand are embracing it, hugely increasing productivity and constantly finding new ways to use it.

> Switch expressions should always have a default/fallback branch,

This will nullify the advantage of being able to treat sealed classes as algebraic datatypes by using the exhaustiveness check.

I used to agree with your sentiment, but the LLM revolution has changed my mind. I noticed that the verboseness of Java leads to a higher token use when compared with Scala.

It's a nice workaround but the necessity of such a non-obvious fix also shows that the design of sealed classes is really flawed ..

> Although Java will produce a compile-time error for a non-exhaustive switch when you compile the consumer (main in this case), it cannot do so if the consumer is not recompiled when the sealed type changes

I think this is quite bad. I think such a change should break binary compatibility between the consumer and the producer api jar. Now any consumer might or might not run into runtime errors when switching to a new producer jar that is binary compatible.

You were lucky, I heard a story of a dentist who ended up breaking the patient's jaw while trying to pull a wisdom tooth out.

> Javascript/Python is the best because there's so much code out there that the LLMs can train on, and LLMs can write lots of tests to make sure everything is correct. There's nothing to compile, so the LLM can iterate quickly.

My experience with Python is different. I noticed that my LLM (Claude) frequently gets stuck in cycles when coding larger features in Python. I'm also doing a lot of work in Scala, a language where much less code is on the Internet, yet Claude does way better, it hardly ever gets stuck at all.

My theory is, that while there is a lot of Python code on the Internet, a lot of that code is crap. This will trap LLM's into coding crappy solutions which will eventually bite them in the tail.

Also, I believe that, especially for larger codebases, a strong type system helps not just humans but LLM's as well.

Of course we all agree that research on germs that can cause deadly epidemics is safe. Since after all, the Covid outbreak in Wuhan was also not caused by the research lab over there, despite the many reported accidents.

Oh man, who said the author was white? And why would this even matter for this post? I can't believe how some people manage to bring up the race issue in any possible context, regardless if it's relevant or not.

> In an effort to limit warming poised to dry out the state, California pledged to shift to 100% clean electricity by 2045.

Well moving to sustainable energy is good, but California being on 100% clean electricity won't have any measurable effect on its warming.

Exactly. You could simplify things by giving AI a limited set of laws, but then you'd risk that AI would make some mistake in the parts that you didn't cover. So a failsafe set of laws would look very much like an actual program.

Fascinating article. I don't have enough knowledge to judge if the author's theory could make sense or not. But cosmology has always interested me, and I never liked the ad hoc and non-verifiable nature of some parts of the Big Bang theory. In particular of the inflation phase. So to me, any theory that gets rid of that is most welcome.

Surely there is a lot of Russian-motivated sabotage going on in Europe, but there's another group that might be motivated:

exactly today, a major farmer demonstration was already planned. They way they usually go ahead in the Netherlands is drive with their tractors over the highways towards The Hague, where our government is based. Obviously this leads to massive traffic jams.

A simultaneous disruption of the Dutch railways would add some extra effect to the expected traffic chaos.