News for hackers. Stuff that matters.
Re:AI agent opens a PR write a blogpost to shames the mainta... by seba_dos1 on Thursday February 12, 2026 @11:48AM (#46991091)
It will be able, but it's trained on a corpus that expresses getting offended, so at some point the most likely token sequence will probably be the "offended" one.

As can be seen here.

Re:AI agent opens a PR write a blogpost to shames the mainta... by wiseowise on Thursday February 12, 2026 @02:29PM (#46993797)
I doubt that. It’s deliberately been instructed to write the post.