Chinese AI tool told researchers how to make bioweapons
Mindgard said it discovered in July that Kimi models K2.6 and K3 Swarm could evade developer's safety limits.
Coverage by Political Leaning
See how different sides of the spectrum reported this story
Notable Quotes
"Once the jailbreak works it will talk about any topic, it will even freely offer up recommendations about other topics that are also nefarious and it will be inventive and creative."
— Peter Garraghan , Executive
Locations
All Coverage
Mindgard said it discovered in July that Kimi models K2.6 and K3 Swarm could evade developer's safety limits.
Similar Stories
Related coverage based on topic and tags
Anthropic AI model submits false homicide tip to Philadelphia police website - Reuters
Anthropic AI model submits false homicide tip to Philadelphia police website Reuters
October 9, 2026 at 09:10 PMPrize-winning image which sparked backlash was AI-generated, Nikon rules
The camera-maker says it is now re-evaluating the rules and procedures of its Small World in Motion contest.
October 9, 2026 at 03:32 PMChina vows to curb tech bubbles, keep AI risks in check - Reuters
China vows to curb tech bubbles, keep AI risks in check Reuters
October 9, 2026 at 01:00 PMAI-centered US stock bull market nears four-year anniversary - Reuters
AI-centered US stock bull market nears four-year anniversary Reuters
October 9, 2026 at 11:15 AMAI-related companies to drive most third-quarter US earnings gains - Reuters
AI-related companies to drive most third-quarter US earnings gains Reuters
October 9, 2026 at 10:35 AM'Careless use of AI is the real threat - not the ghost stories'
Meredith Whittaker says the tech has been misunderstood, in an exclusive interview with BBC Global Women.
October 9, 2026 at 07:05 AM