How Anthropic made its powerful Fable 5 model safe to deploy again, ending a global shutdown
- 9 minutes ago
- 1 min read
INC. — The company also said they will continue to update their classifiers as more “novel jailbreak techniques” come to light and will work with Amazon, Google, Microsoft and partners in their in-house Glasswing program to draft a “consensus framework” to develop better safety features.
Finally, they said they would also work with the U.S. government on model testing and safeguards.
Read the full story | INC.
