Yeah I don't know that any of the benchmarks index on "understandability". I'm amazed at how Claude can produce a page of text describing what it did and it can take me a full five minutes to decipher it, often just to find it's something I could have expressed in a simple sentence.

▲

sshine 3 hours ago | parent | next [-]

I just spent a day writing very thorough system prompts for communicating in different contexts.

Everything is super succinct. Opus 5 lands, it almost completely disregards the intent.

I suppose watermarking requires a certain text mass.

▲

CuriouslyC an hour ago | parent | next [-]

The watermarking is going to get rolled back or Anthropic is going to get rolled. People hate it and it makes the writing worse.

▲

causal 3 hours ago | parent | prev [-]

Oh man. Hadn't even considered the watermarking angle.

▲

Retr0id 2 hours ago | parent [-]

The simpler angle is that more text lets them bill you more. I don't think that was necessarily their intent, but it does mean they have a negative incentive to fix it.

	▲	StilesCrisis an hour ago \| parent [-]
		I would have assumed reasoning tokens dramatically outweigh user-visible output. It certainly seemed that way when they were visible!

▲

jasonlotito 2 hours ago | parent | prev | next [-]

Adjust the output in settings. Or customize it to what you want.

▲

conception 3 hours ago | parent | prev [-]

Have you tried asking it for a lay explanation of what it did? That’s usually all it takes for me. Sends garbage -> request -> sends something readable

	▲	anon7000 10 minutes ago \| parent \| next [-]
		No, I’m not interested in fighting my model all day long. Plus is fucking annoying to talk to and collaborate with, so I’m not using it when Sol 5.6 is about 1000 times better in that regard. I have colleagues who spent a lot of time trying to improve their harness with user rules and whatnot and Opus really does not want to follow them.
	▲	basch 2 hours ago \| parent \| prev \| next [-]
		Brilliant way to get people to waste tokens. Maybe just don’t generate garbage in the first place?
	▲	StilesCrisis an hour ago \| parent \| prev \| next [-]
		When I ask it to make a CL description, it's worthless unless I tell it to dumb it down as much as possible, assume the reader has zero knowledge of the codebase. And then it makes a perfectly cromulent description that just needs a touch of trimming-down. If I don't do this, the description is just a wall of gibberish and paraphrasing of every little thing it encountered.
	▲	D13Fd 2 hours ago \| parent \| prev [-]
		Yeah but Sol shows it is possible to just send the readable explanation in the first instance. And I don't want to spend tokens and time on asking for a better version of each response.