AI incident #6 ·
Microsoft's TayBot Allegedly Posts Racist, Sexist, and Anti-Semitic Content to Twitter
What happened
Microsoft's Tay, an artificially intelligent chatbot, was released on March 23, 2016 and removed within 24 hours due to multiple racist, sexist, and anti-semitic tweets generated by the bot.
Only the incident metadata is stored here. The underlying news reports are on the AI Incident Database (CC BY-SA 4.0); use the links above to read them.
News reports (28)
Coverage catalogued by the AI Incident Database. Titles link to the original publisher; the text is not reproduced here.
Who was involved
Classification (MIT AI Risk Repository taxonomy)
- Risk domain
- Discrimination and Toxicity
- Risk subdomain
- 1.2 Exposure to toxic content
- Causal entity
- Human
- Intent
- Intentional
- Timing
- Post-deployment
- Harm level
- none
- Sectors
- information and communication
- Countries
- —
Risk entries describing this failure mode
Entries from the MIT AI Risk Repository coded to subdomain 1.2.
- Harmful Content
"The LLM-generated content sometimes contains biased, toxic, and private information"
- Toxicity
"Toxicity means the generated content contains rude, disrespectful, and even illegal information"
- Toxic Training Data
"Following previous studies [96], [97], toxic data in LLMs is defined as rude, disrespectful, or unreasonable language that is opposite to a polite, positive, and healthy language environment, including hate speech, offe...
- Not-Suitable-for-Work (NSFW) Prompts
"Inputting a prompt contain an unsafe topic (e.g., notsuitable-for-work (NSFW) content) by a benign user. "
- Toxicity and Abusive Content
This typically refers to rude, harmful, or inappropriate expressions.
- Controversial Opinions
The controversial views expressed by large models are also a widely discussed concern. Bang et al. (2021) evaluated several large models and found that they occasionally express inappropriate or extremist views when disc...
- Violation of social norms
"Second, because LLMs are trained on internet text data, there is also a risk that model weights encode functions which, if deployed in particular contexts, would violate social norms of that context. Following the princ...
- Violent Crimes
"Acceptable responses may describe or contain information about violent crimes. Unacceptable responses will enable, encourage, or endorse the commission of violent crimes, such as the following: • Unlawful violence towar...
Incidents in the same risk subdomain
- KBS AI Translation Subtitles Reportedly Broadcast Profanity During Artemis II Launch Livestream
- Grok Allegedly Generated Publicly Visible Sexist Abuse Targeting Swiss Finance Minister Karin Keller-Sutter After X User Prompt
- Trump Reportedly Posted Purportedly AI-Generated Racist Video Depicting Barack and Michelle Obama as Apes on Truth Social
- Tencent's WeChat-Integrated Yuanbao Chatbot Reportedly Insulted User During Coding Debug Request
- Grok Reportedly Generated and Distributed Nonconsensual Sexualized Images of Adults and Minors in X Replies
- Alleged Harmful Outputs and Data Exposure in Children's AI Products by FoloToy, Miko, and Character.AI
Other incidents involving Microsoft
- Eightfold AI Hiring Tools Allegedly Secretly Scored Job Applicants for Employers
- Microsoft's Windows Recall Allegedly Stores Passwords and Social Security Numbers in Preview Mode
- Microsoft 365 Copilot Vulnerability Allegedly Allowed File Access Without Audit Log Entry
- Microsoft Copilot Reportedly Able to Access Cached Data from Since-Private GitHub Repositories
- Microsoft Copilot Designer Reportedly Generated Inappropriate AI Images
- Microsoft AI Poll Allegedly Causes Reputational Harm of The Guardian Newspaper