Techly NewsGet the app

Get the latest tech news

Syntax hacking: Researchers discover sentence structure can bypass AI safety rules


New research offers clues about why some prompt injection attacks may succeed.

None

Get the Android app

Or read this on ArsTechnica

Read more on:

Photo of researchers

researchers

Photo of syntax

syntax

Photo of Syntax hacking

Syntax hacking

Related news:

News photo

AI Can Already Do the Work of 12% of America's Workforce, Researchers Find

News photo

Mind-Altering 'Brain Weapons' No Longer Only Science Fiction, Say Researchers

News photo

Poets are now cybersecurity threats: Researchers used 'adversarial poetry' to trick AI into ignoring its safety guard rails and it worked 62% of the time

« Canonical Now Offering Ubuntu Pro For WSL
M64 colors: every colorway available for ModRetro’s N64 revival »