Re:How Claude marks AI-generated content
by noman-land on Monday August 10, 2026 @09:02PM
(#49252000)
It's pretty trivial to command it to not speak that way. That's one of the first things you should write into the prompt. What style you want it to write in. Make it use a very concise and dry academic style with no overt LLMisms, melodramatic or flowery language, or metacommentary.
[ Parent
| on HN ]
Re:How Claude marks AI-generated content
by breezybottom on Tuesday August 11, 2026 @08:24AM
(#49257179)
People have been posting some variant of this comment for three years, and it's no more true today. Ever notice that the "prompt engineer" career hasn't materialized?
Re:How Claude marks AI-generated content
by someguynamedq on Tuesday August 11, 2026 @09:55AM
(#49258427)
Prompt engineer is a requirement within every serious job now, not a job in itself
Re:How Claude marks AI-generated content
by breezybottom on Tuesday August 11, 2026 @03:42PM
(#49263413)
I've never known any firefighters to prompt engineer a blaze, but perhaps you don't consider that a "serious" job.
Hey ChatGPT, what side should I make the incision on?
Re:How Claude marks AI-generated content
by noman-land on Tuesday August 11, 2026 @09:07AM
(#49257696)
Regular engineers still exist.