play1.x with scala was quite experimental (play2 is really different and robustly designed) and those benchmarks always generate trolls... Anyway, I can't make people change their mind about those points even if I had numbers to show because everyone sees what he wants to see. This is just subjectivity ;)
You're welcome!
The idea is to simplify writing basic Reads/Writes for simple Scala structures. In this way, you can focus on writing more complex JSON validation/transformation when you need it... For JSON coast-to-coast design that I introduced in previous article, this is quite useful!
And Play2 core is composed of very robust components without any runtime enhancement, any magic. Using Scala power, we can build very clean tools, such as this one, without perverting typesafe/fully-compiled basements.
There was a long email thread on the play framework, but as someone who is doing Play 2/Scala, they're nothing even close to the same framework, enough that calling it the same name is silly. Further, the deprecation of Play 1 does no favors, and I'm just hoping that as things go forward, a fork will emerge.
I'm also hoping that Play 2 will stop taking so ing long to compile longer projects. Is 2.1 going to make me not want to claw my eyes out?
It depends on your mindset. I use both and love both but when it comes to massive changes on critical components in huge codebases give me static typing every time.
typesafety+compiled brings a robustness and sureness (and sometimes performance) that dynamic languages can't really provide. Dynamic languages are interesting in some domains also... I must admit I'm a big fan of static typed language since the beginning so I'm not really objective ;)
This new driver mixed with Play2 fully non-blocking/asynchronous stack opens very interesting fields of exploration and was really something missing till now in JVM world...