News for hackers. Stuff that matters.

A comment on GPT-5.6. Parent comment

Re:GPT-5.6 by astrange on Thursday July 09, 2026 @03:57PM (#48851596)
> LLMs seem particularly bad at writing prompts for other LLMs for this reason

Claude is terrible at this! Probably for the same reason that its writing style in prose is so annoying and full of claudisms.

[ Parent | on HN ]
Re:GPT-5.6 by irthomasthomas on Thursday July 09, 2026 @07:19PM (#48853719)
Claude use to be leader, too. Their metaprompt was great at the time with opus 3
[ Parent | on HN ]