Fable 5 AI Model
Curated by the Inblix editorial team
The US government has lifted its two-week ban on Anthropic’s Fable 5 AI model, making it available worldwide again after addressing a security vulnerability that allowed it to be ‘jailbroken’. The model was restricted due to its ability to identify software vulnerabilities and produce code to exploit them. Anthropic has since trained a new filter to block such requests, but it also flags harmless programming tasks more often. Why it matters: this incident highlights the ongoing challenges of ensuring AI safety and security, and the need for industry-wide standards to address these issues.
💡 Key Takeaways
- The US government has lifted its ban on Anthropic's Fable 5 AI model after a two-week suspension
- A new filter has been trained to block requests that could bypass the model's safety guardrails, but it also flags harmless tasks more often
- Anthropic and other industry leaders are working to develop a shared standard for rating jailbreaks and triggering countermeasures
Keep reading: See related articles below for more coverage on this topic.
Get smarter about AI
The sharpest AI news, curated daily. Delivered free to your inbox.