They've corrupted their data set by padding it with generated slop, in the misguided belief that you need 10PB of data to train a brain. Every training round they load more AI slop into it, further amplifying the slop language.

It's fascinating, Sonnet 4 is still available via API and it's so much less moronic than the current model. All of the em-dashes and nonsense are a result of the repeated rounds of reinforcement learning using slop data.

▲

jp57 7 hours ago | parent [-]

But why did that style of writing get rewarded? The people at Anthropic are ultimately responsible for the reward signal and what it produced.

▲

visarga 6 hours ago | parent [-]

I blame it on their focus on "persona design". They botched it.

	▲	cruffle_duffle 6 hours ago \| parent [-]
		"They botched it." <-- sure, but worse.... they shipped it anyway. And that is the part that gets me. It's a vastly worse product than it was on like 4.6. I suppose you can (and should) use opus 4.6 -- they do make it available still. Then just treat 5 as something you avoid until they push out a new version.