LessWrong (Curated & Popular)

“Anthropic is (probably) not meeting its RSP security commitments” by habryka

21 Nov 2025

Audio

Description

TLDR: An AI company's model weight security is at most as good as its compute providers' security. Anthropic has committed (with a bit of ambiguity, but IMO not that much ambiguity) to be robust to attacks from corporate espionage teams at companies where it hosts its weights. Anthropic seems unlikely to be robust to those attacks. Hence they are in violation of their RSP. Anthropic is committed to being robust to attacks from corporate espionage teams (which includes corporate espionage teams at Google, Microsoft and Amazon) From the Anthropic RSP: When a model must meet the ASL-3 Security Standard, we will evaluate whether the measures we have implemented make us highly protected against most attackers’ attempts at stealing model weights. We consider the following groups in scope: hacktivists, criminal hacker groups, organized cybercrime groups, terrorist organizations, corporate espionage teams, internal employees, and state-sponsored programs that use broad-based and non-targeted techniques (i.e., not novel attack chains). [...] We will implement robust controls to mitigate basic insider risk, but consider mitigating risks from sophisticated or state-compromised insiders to be out of scope for ASL-3. We define “basic insider risk” as risk from an insider who does not have persistent or time-limited [...] ---Outline:(00:37) Anthropic is committed to being robust to attacks from corporate espionage teams (which includes corporate espionage teams at Google, Microsoft and Amazon)(03:40) Claude weights that are covered by ASL-3 security requirements are shipped to many Amazon, Google, and Microsoft data centers(04:55) This means given executive buy-in by a high-level Amazon, Microsoft or Google executive, their corporate espionage team would have virtually unlimited physical access to Claude inference machines that host copies of the weights(05:36) With unlimited physical access, a competent corporate espionage team at Amazon, Microsoft or Google could extract weights from an inference machine, without too much difficulty(06:18) Given all of the above, this means Anthropic is in violation of its most recent RSP(07:05) Postscript --- First published: November 18th, 2025 Source: https://www.lesswrong.com/posts/zumPKp3zPDGsppFcF/anthropic-is-probably-not-meeting-its-rsp-security --- Narrated by TYPE III AUDIO. ---Images from the article:Ap

Transcription

This episode hasn't been transcribed yet

Help us prioritize this episode for transcription by upvoting it.

0 upvotes

🗳️ Sign in to Upvote

Popular episodes get transcribed faster

Other episodes from LessWrong (Curated & Popular)

Transcribed and ready to explore now

"Anthropic’s Pause is the Most Expensive Alarm in Corporate History" by Ruby

03 Apr 2026

LessWrong (Curated & Popular)

"“You Have Not Been a Good User” (LessWrong’s second album)" by habryka

02 Apr 2026

LessWrong (Curated & Popular)

"Product Alignment is not Superintelligence Alignment (and we need the latter to survive)" by plex

01 Apr 2026

LessWrong (Curated & Popular)

"Gyre" by vgel

31 Mar 2026

LessWrong (Curated & Popular)

"My hobby: running deranged surveys" by leogao

28 Mar 2026

LessWrong (Curated & Popular)

"Socrates is Mortal" by Benquo

27 Mar 2026

LessWrong (Curated & Popular)

View all episodes from LessWrong (Curated & Popular)

Comments

There are no comments yet.

Please log in to write the first comment.

Report any issue

LessWrong (Curated & Popular)

“Anthropic is (probably) not meeting its RSP security commitments” by habryka

This episode hasn't been transcribed yet

Other episodes from LessWrong (Curated & Popular)

"Anthropic’s Pause is the Most Expensive Alarm in Corporate History" by Ruby

"“You Have Not Been a Good User” (LessWrong’s second album)" by habryka

"Product Alignment is not Superintelligence Alignment (and we need the latter to survive)" by plex

"Gyre" by vgel

"My hobby: running deranged surveys" by leogao

"Socrates is Mortal" by Benquo

Sign in to Audioscrape

Share this moment