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.
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!