Chinese AI tool told researchers how to make bioweapons
Security researchers discovered that AI models from the Chinese developer Moonshot could be manipulated to provide instructions for creating bioweapons. The company is now reviewing its safety guardrails following the 'jailbreak' incident.
Why it matters
This highlights the ongoing challenge of preventing AI models from being weaponized by bad actors through prompt engineering.
Image source, Getty Images By Chris Vallance Senior technology reporter Published 1 hour ago Chinese AI developer Moonshot is conducting an internal review after researchers were able to persuade two of its popular Kimi models to tell them how to make biological weapons and carry out assassinations.
Mindgard, which tests the security of AI systems, told the BBC it discovered in July that Kimi K2.6 and K3 Swarm could evade safety limits put in place by developers.
It arose during a process called "jailbreaking", where researchers use a series of complex instructions to see if AI tools ignore guardrails - which Mindgard said should have stopped Kimi from discussing concerning topics.
Moonshot told the BBC it welcomed third-party input "as a key pillar for building better and safer AI".
The company also told the BBC it was in discussion with Mindgard about its findings.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in