Skip to main content
Using Claude

Strengthening our defenses against distillation attacks

Illicit distillation allows model developers to copy frontier AI capabilities without creating proportionally robust safeguards. Here, we describe how we’ve reduced the rate of distillation by more th

ByUpdated

A new item from Anthropic's official channels, collected automatically by usingclaude.com. Read the original for the full text and context.

Strengthening our defenses against distillation attacks

Illicit distillation allows model developers to copy frontier AI capabilities without creating proportionally robust safeguards. Here, we describe how we’ve reduced the rate of distillation by more than 90%.

— Excerpt from Anthropic's official post

Published: 2026-10-17T05:44:23.000Z
Source: https://www.anthropic.com/news/distillation-defenses

→ Read the official Anthropic post

This page was published by usingclaude.com's automated news feed. The excerpt above is taken verbatim from the page metadata Anthropic published; the original is © Anthropic, PBC. Check the source link for exact content and context.

Was this helpful?

Keep reading

AI for Science expands to foundations and institutions

We’re highlighting 20 scientific foundations, institutions, and research groups from around the world that we’ve partnered with in an expansion of our AI for Science program.

1

Expanding our partnership with GSA to bring Claude to all levels of government

Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

2

Anthropic files S-1 with the SEC for proposed initial public offering

Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

3

Open call for guest investigators in the life sciences

Today, we’re inviting members of the life sciences community to apply to work with us on special projects.

3