alt Hacker NewsEverything that claude writes fits into the same aesthetic structure. The aesthetic is that of an expert slowly revealing an insight to the user. The actual content doesn't matter.
- "Introduction that rephrases your prompt."
- "3 paragraphs, with one section of bullet points"
- "The Twist"
- "The Bottom Line"
It's really obvious once you see it. Every single prompt, from a quantum physics question to a mundane observation about California burritos, is phrased in exactly the same way. This is obviously an artifact of post-training but it's also kind of how you can tell that this thing is a lot closer to a blindsight scrambler than real intelligence.
Replies
It's the same way how every AI generated poster looks exactly the same. As if there is a single underlying prompt that describes the template of the poster/long-form article, and it does not dare deviate from that.
I've noticed that ChatGPT (whatever model the free version uses by default) likes to phrase answers as though it's correcting me, even when my question doesn't contain any assumptions.
The second bullet point, down to the comma in the middle of the sentence, is what has been driving me absolutely batty of late. It's a surefire tell that I cannot seem to beat out of my outputs. It CONSTANTLY does it, even when you say not to.
Between that and the insistence on "this, not that" structure makes me want to install the caveman skill and use it even for non-code workflows.
In your reading, what is the distinction between blindsight’s scrambler and real intelligence? My reading is that it’s just as real, and draws out the disadvantages a sense of self constrains intelligence with
Perhaps this is related to their new "invisible watermark" concept which would probably require rather contrived language patterns to make possible.
At this point, I'm basically telling models to not write any English text or prose. Only write code. They are great at writing code. Not so great at writing good English. In software projects, lengthy comments and docs are an anti-pattern: the software should instead be written to do the right expected thing so that you don't have to think about it. I don't want all these tokens polluting my context, either.