Agree completely. Compared to just a few months ago, I spend what feels like 10x more time reading long-winded, alien-jargon laced over-explanations for some simple task Claude just finished, followed by a list of strange suggestions for what to do next, these suggestions will use strange words that reference a strange phrase it uttered somewhere in it's dialog, so don't try and skim through claude's response because you'll need to know WTF it's talking about in order to respond to it's suggestions. It's getting super exhausting. The good news is that it has pushed me toward using my local models more often and eventually they will replace my anthropic account en masse.

▲

rubicon33 12 hours ago | parent [-]

Totally agree. AI has gone completely off the rails with weird language, that is frankly hard to follow. It's suggestions are often quite difficult to reason about and I think that has more to do with the models choices than with our distance from the code. It could make much simpler, clearer, more helpful suggestions but often makes convoluted suggestions that might be technically right but make no sense.

	▲	spottedmarley 12 hours ago \| parent [-]
		Claude dumps 3 pages of response, you try to read some of it but it's so fragmented and weird, so you skim to the bottom to see what it's asking for next and it says something like "Do you want me to charge the gap on cell length fortification or drop the bagel bites on stdout with Q1 and Q3 before testing the edges on spec? Say the word and I'll refactor the baseline.", and you're like "WTF is Q1 and Q3? Bagel bites? Am I tripping? I've never heard of any of these terms before. Have I been hacked?" LoL