Get the latest tech news

Add one more AI worry to the nightmare scenario: self-replicating prompt injections

It's a worm attack, AI-style

None

Get the Android app

Or read this on The Register

Read more on:

Photo of self

self

Photo of nightmare scenario

nightmare scenario

Related news:

EXCLUSIVE: AI researchers warn companies rushing self-improving systems despite safety risks

Comma's self-driving kit for older cars faces federal probe after 5 crashes

Anthropic, OpenAI Executives Urge Oversight of Self-Improving AI

« BMW’s revamped i3 boasts up to 468 miles of range

As AI models go rogue, do you still trust OpenAI and Anthropic to stop them? I don’t and neither should you »