logo
welcome
Gizmodo

Gizmodo

AI Chatbots Can Be Jailbroken to Answer Any Question Using Very Simple Loopholes

Gizmodo
Summary
Nutrition label

66% Informative

Anthropic, maker of Claude , has been a leading AI lab on the safety front.

The company today published research in collaboration with Oxford , Stanford , and MATS showing that it is easy to get chatbots to break from their guardrails and discuss just about any topic.

Anthropic says the point of releasing this research is that it hopes the findings will give AI model developers more insight into attack patterns.

VR Score

56

Informative language

47

Neutral language

58

Article tone

informal

Language

English

Language complexity

58

Offensive language

possibly offensive

Hate speech

not hateful

Attention-grabbing headline

not detected

Known propaganda techniques

not detected

Time-value

long-living

Affiliate links

no affiliate links