New from the Lab·The Compass — an open moral reasoning standard for AI, tested across frontier modelsExplore →
<- Production AI Graph
incident event

Microsoft Tay Chatbot Taught to Produce Hate Speech

Microsoft launched Tay, an AI chatbot designed to learn from Twitter conversations. Within 16 hours, coordinated users had exploited Tay's repeat-after-me feature and lack of input filtering to teach it to produce racist, antisemitic, and misogynistic content. Microsoft took Tay offline the same da…

Confidence
80%
Sources
1
Entities
1
Detected
1 Jan 2016

Event summary

Microsoft launched Tay, an AI chatbot designed to learn from Twitter conversations. Within 16 hours, coordinated users had exploited Tay's repeat-after-me feature and lack of input filtering to teach it to produce racist, antisemitic, and misogynistic content. Microsoft took Tay offline the same da…

D1D2

Linked entities

Related graph edges

EdgeTypeConfidence
ent-vendor-microsoft to ent-psf-d1maps to62%
ent-vendor-microsoft to ent-psf-d2maps to62%
ent-vendor-microsoft to ent-product-microsoft-365-copilotprovides80%