Tech
Cybersecurity Researchers Criticize Anthropic's Fable Guardrails
AI Summary
Anthropic's latest AI model, Fable, has been criticized by cybersecurity researchers for its restrictive guardrails, which limit its use for cybersecurity-related tasks. The model is designed to prevent misuse, but experts argue that the restrictions are too broad and hinder legitimate research.
The Limitations of Fable
Anthropic released its latest model Fable on Tuesday, billing it as a public and limited version of its powerful and much-hyped cybersecurity model Mythos. However, not everyone is happy with the restrictions, and a number of cybersecurity researchers and professionals have aired complaints online.The Guardrails Controversy
“[Fable] rejects any request that could be tangentially cyber related. Even innocuous tasks like reading a blog post,” said Valentina “Chompie” Palmiotti, a well-known security researcher who works at IBM X-Force. When a prompt triggers its guardrails, Fable pauses the chat and says that its “safety measures flagged this message for cybersecurity or biology topics.”The Data Analysis
- The guardrails were put in place to limit the risk that Fable could be used to develop malware or compromise software.
- The restrictions on biology come from a similar concern around developing biological weapons.