Get the latest tech news

Microsoft boffins figured out how to break LLM safety guardrails with one simple prompt

None

Get the Android app

Or read this on The Register

Read more on:

Photo of Microsoft

Microsoft

Photo of Simple prompt

Simple prompt

Photo of Microsoft boffins

Microsoft boffins

Related news:

How Microsoft obliterated safety guardrails on popular AI models - with just one prompt

Microsoft Hit With Second Downgrade as Melius Warns on AI Risks

Microsoft: Exchange Online flags legitimate emails as phishing

« YouTube TV Gets Cheaper Sports, News, and Entertainment Bundles

Chinese AI company unveils $173K ‘biometric’ robot built for human companionship »