I frequently find myself instructing Opus 5 to stop overcomplicating things.
It just wants to talk jargon heavy and add unnecessary noise to the conversation.
I wonder it’s related to text watermarking somehow.
It just wants to talk jargon heavy and add unnecessary noise to the conversation.
I wonder it’s related to text watermarking somehow.
I still have some promotional credits and use them with Fable, and the answers are night and day in my particular use case.
I also think this is why the models aggressively drift back to the exact same word choice. You can put it in CLAUDE.md, explicitly prompt it, doesn't matter. A prompt or two later it's back on its bullshit.
I don’t remember where I saw it, but I think there’s also a smaller agent paraphrasing my requests to the agent because I remember being angry and saying aiming sarcastic about an issue and the thinking notes said the user is angry do this blah blah, but then the Claude claim I asked for that specific solution.
I think they’re running some optimizations and multi level agents etc. tests to reduce costs.