Hacker News Reader

Comment by mikepurvis | Hacker News Reader

ChatGPT has been doing that for a long time, like "by the way, can I just say it's funny how xxxxxxx". Always an invitation to continue engaging, which with a human conversation partner you would feel obligated to respond to or at the very least acknowledge.

With a clanker though, no such obligation exists and the "hey also" content (like any other part of the response) can simply be ignored.

View on HN

With Claude it feels like those engagement invitations have turned into things like "By the way, it's worth sitting with this problem I've identified in your assertions..." or "Here's an alarming gap worth resolving in your code..."

Gemini also does the same lighthearted GPT-style invitation with the default prompt in the Google webui, but it doesn't seem to exist on the API. The Claude models seem to have been trained to force this structure on every one of their responses, and until I realized they always stick the same thing in the last part of their response, I found the Claude version more distracting since it's always pointing out an imaginary and supposedly very important problem.

I never got those in codex after like the first day they started appearing. I just added a custom instruction not to do that. I also don't get them in chatgpt web for the same reason?

It's just this in agents.md " Do not "if you want" me. Never provide follow up suggestions. "

Reply on news.ycombinator.com