
US Government Allows Release of Mythos and Fable After Anthropic Adds "Don't Do Bad Stuff" to Harness
Four simple words ended a national security standoff and restored access to Anthropic's two most powerful models: "don't do bad stuff." That is the line engineers added to the model's harness to satisfy a federal commitment to "proactively detect and address security risks." The four words were proposed by Fable 5 itself, which was asked to draft the safeguard governing its own conduct and returned "don't do bad stuff," along with a pinky promise that it would not ignore the instruction.



















