Anthropic said it had made it harder to use proxy networks to repeatedly probe Claude's protected reasoning, blocking extraction attempts and hindering large-scale distillation efforts
Anthropic said it had made it harder to use proxy networks to repeatedly probe Claude's protected reasoning, blocking extraction attempts and hindering large-scale distillation efforts
<iframe src="https://hindustansphere.com/embed/cluster/1cb5f2dbea4e1ea28fd660dfdf3d7632f134f0b3" width="100%" height="320" style="border:0;max-width:680px" loading="lazy" title="New safeguards sharply reduce AI distillation attacks, says Anthropic"></iframe>
Anthropic said on Monday new measures designed to prevent rivals from copying the capabilities of its Claude AI models have reduced data harvested in so-called distillation attacks
