'Positive review only': Researchers hide AI prompts in papers

Re:'Positive review only': Researchers hide AI prompts in pa... by IshKebab on Saturday July 05, 2025 @02:12PM (#44474462)

Agent-style AI can run shell commands. You have to accept them but some people live dangerously and say Yes To All.

[ Parent | on HN ]

Re:'Positive review only': Researchers hide AI prompts in pa... by PickledChris on Saturday July 05, 2025 @03:02PM (#44474773)

I've been letting Gemini run gcloud and "accept all"ing while I've been setting some things up for a personal project. Even with some limits in place it is nervewracking, but so far no issues and it means I can go and get a cup of tea rather than keep pressing OK. Pretty easy to see how easy it would be for rogue AI to do things when it can already provision its own infrastructure.

[ Parent | on HN ]

Re:'Positive review only': Researchers hide AI prompts in pa... by qingcharles on Saturday July 05, 2025 @03:57PM (#44475103)

Sadly, this was the last time anybody heard from PickledChris.

[ Parent | on HN ]

Re:'Positive review only': Researchers hide AI prompts in pa... by snickerbockers on Wednesday July 09, 2025 @01:22PM (#44512635)

"Open the brine valve HAL."

"I'm sorry Chris. I'm afraid I can't pickle that."

[ Parent | on HN ]

Re:'Positive review only': Researchers hide AI prompts in pa... by helloplanets on Saturday July 05, 2025 @02:18PM (#44474510)

Yep, it's not as far fetched as it would've been a year ago. A scenario where you're running an agent in 'yolo mode', it opening up some poisonous readme / docs / paper, and then executing the wrong shell command.

[ Parent | on HN ]

Re:'Positive review only': Researchers hide AI prompts in pa... by nerdsniper on Saturday July 05, 2025 @02:49PM (#44474687)

Could be done responsibly if you run it in a VM to sandbox it with incremental backup so you can roll-back if something is deleted?

[ Parent | on HN ]