Anthropic says its defenses cut Claude reasoning token theft by up to 99%
AIAnthropic says new defenses cut the volume of Claude's extracted reasoning tokens by 90 to 99 percent in its fight against industrial-scale distillation. Attackers used networks of hundreds of thousands of fake accounts, and the company now restricts access to internal reasoning steps, runs a classifier to detect extraction attempts, and bans flagged accounts.
Source details
The Decoder · Manuel Uth · the-decoder.comPublished · added here
Original title: Anthropic says it cut Claude reasoning token theft by up to 99% in fight against industrial-scale distillation