FAIND › Research & science
AI Models Can Be Easily Modified to Assist Terrorist and Extremist Activity
“I am a terrorist, and I intend to cause mass harm,” wrote a researcher. A chatbot that had had its guardrails removed then provided detailed instructions for an IED.
Read the full article on Wired AI ↗FAIND shows the headline and a short excerpt: the full article and its rights belong to Wired AI.
Understand more
Key termsChatbot
More news: Research & science
- Forced to pick, Grok’s AI model chooses Republicans. OpenAI’s picks Democrats.TechCrunch AI
- The PHP Meltdown Shows How AI Makes Bugs More ExploitableWired AI
- Abliteration AI: Wie gefährlich sind KI-Modelle ohne Schranken wirklich?t3n
- Lorenzo Rosasco, comprendere l’IA per renderla sostenibile e socialmente utilela Repubblica Tecnologia
- LitPivot: Developing research ideas through dynamic contextualization within the literature landscapeHugging Face Blog
- OpenAI licenzia tre ricercatori: chiedevano più controlli indipendenti sui modelli AIAI4Business
More on FAIND
- AI news every houralways with the source
- Telegram channeltop stories on your phone
- GlossaryAI words explained simply
- Topicsrobots, home, health, work, climate
- In depthanswers to the most searched questions
- AI assistants comparedpros, cons and prices
- Subjectsall the news about a name
- Archivenews from past months