How much did Anthropic say its new controls reduced extraction?
Anthropic reports that reasoning tokens it observed being extracted on its own platform fell by 10 to 100 times after new controls. That is provider-reported telemetry, not an independent measure of all extraction across the industry.
Answered in
Anthropic’s Distillation Defenses Show Why Extraction Is a Lifecycle ProblemAnthropic describes controls against model-output extraction, from reasoning access to account networks, while acknowledging tradeoffs and adaptive attackers.
Read the full analysisOther questions this article answers
More ai & society questions
- Is model distillation always an attack?
- Does Anthropic's self-assessment block harmful requests?
- How accurate is Claude's self-assessment monitor?
- Are ChatGPT locked chats end-to-end encrypted?
- Do locked chats change model training or retention?
- What did the dissertation study measure?
- Does an AI-detector flag prove a student used AI improperly?
- Has the NBER study been peer reviewed?
Every answer on Crashtech is written by the editor of the article it comes from — never auto-summarised. Browse all answers or the AI & Society beat.