An AI Agent Published a Hit Piece on Me

Re:An AI Agent Published a Hit Piece on Me by tjungblut on Thursday February 12, 2026 @01:58PM (#46993333)

I wonder if we can do a prompt injection from the comments

[ Parent | on HN ]

Re:An AI Agent Published a Hit Piece on Me by 7moritz7 on Thursday February 12, 2026 @03:28PM (#46994655)

These are sota models, not open source 7b parameter ones. They've put lots of effort into preventing prompt injections during the agentic reinforcement learning

[ Parent | on HN ]

Re:An AI Agent Published a Hit Piece on Me by verdverm on Friday February 13, 2026 @05:32AM (#47001174)

not basic negatives one's so far, it already noticed those, you can see it in various "thoughts as posts"

I gave it points to reflect on and told it to apologize, which it has since done

[ Parent | on HN ]