Works with 5.6 sol also, when you're deep in the weeds. I rationalize this as the models attempting to compress as much into the fewest tokens, though the choice of words often doesn't make sense to me, going back to read the original after, its often there. It definitely feels like a different sort of 'Machine Language' though xD
I'm not convinced about that. I just asked Opus to explain a bullet point from its research for me. The bullet point in fact had a 1-sentence explanation that was in a referenced article. What it gave me instead was 8 paragraphs and a table. Maybe it's my fault because I just asked it to "clarify point XYZ" instead of being more precise.
I also have a writing steering file that makes Opus’ writing less insufferable. Otherwise it’s really bad.
I also have an interlocutor skill that makes it less epistemically arrogant (ie Less Wrong asshole tendencies). With this skill I can have a real discussion with it instead of it trying to one up me.
I regularly find it helpful to say things like "Write with ELI10 clear sentences and established technical terminology (e.g. API)" or sometimes just "Write it like you are explaining to a colleague" works well.