I had a similar thought but I assumed they leaned in because it improved performance on coding or something like that

kingstnap 11 hours ago | parent | next [-]

It could also partly be a byproduct of examples of claude writing being in the dataset, which of course anthropic has lots and lots of and they do train on.

	▲	r_lee 36 minutes ago \| parent [-]
		no way. there's just no good excuse for why "load-bearing" and "worth flagging" are everywhere now, I've pretty much never seen that in the wild before

▲

LoganDark 11 hours ago | parent | prev [-]

I suspect it's because of alignment concerns. The more deeply they can integrate their principles, the harder it'll be to misuse. Or at least that's the idea.