Hacker News Reader

Comment by causal | Hacker News Reader

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.

View on HN

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.

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

Nah no one will notice. Gemini already does this and openai will soon do this as well.

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

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.

I would have assumed reasoning tokens dramatically outweigh user-visible output. It certainly seemed that way when they were visible!

They want you to use Sonnet to explain what Opus is trying to say. They're not optimizing for token efficiency.

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

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

Brilliant way to get people to waste tokens.

Maybe just don’t generate garbage in the first place?

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.

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.

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.

Yeah my trick is "Restate concisely"

Just those two words. I use it A LOT recently.

Reply on news.ycombinator.com