logoalt Hacker News

roywigginstoday at 12:20 AM2 repliesview on HN

It's all fine until OpenClaw decides to start prompt injecting the judge


Replies

bambaxtoday at 2:04 AM

Exactly; would probably be safer with a purely algorithmic decision making system.

fc417fc802today at 1:50 AM

Calling it now. Show HN: Pincer - A small highly optimized local model to detect prompt injection attempts against other models.

show 1 reply