5
DEF CON Contest Sees Hackers Expose AI Inaccuracies and Biases
source link: https://nextbigwhat.com/def-con-contest-sees-hackers-expose-ai-inaccuracies-and-biases/
Go to the source link to view the article. You can view the picture content, updated content and better typesetting reading experience. If the link is broken, please click the button below to view the snapshot at that time.
DEF CON Contest Sees Hackers Expose AI Inaccuracies and Biases
- Hackers test eight AI models from Google, Meta Platforms, and OpenAI at a public contest during the DEF CON conference, revealing biases and errors.
- The White House supports the endeavor to push for the development of new restrictions to manage AI system issues.
- Insights reveal AI models may endorse harmful speech, offer illegal instructions, and spread misguided facts while struggling to avoid all attacks.
Recommend
About Joyk
Aggregate valuable and interesting links.
Joyk means Joy of geeK