Anthropic restores Fable 5 after deploying a stronger cyber classifier
Anthropic restored global Fable 5 access after training a classifier that blocked the reported bypass in more than 99 percent of tests and obtaining independent US government safeguard testing; restricted Mythos 5 access also resumed for approved US organizations.
0 comments · 0 votes
Sign in to join the discussion →
No comments yet. Start the discussion.
Why it moved the index
The dated first-party account documents a targeted classifier trained in response to Amazon's reported bypass, a greater-than-99-percent block rate on that technique, and independent CAISI testing before access resumed. The mitigation is practical and externally tested, but it covers one reported technique and broader redeployment increases exposure, so the net away-from-doom magnitude is limited.
Assessment history
-
R1
Away 28 · confidence 87
Distinct completed safeguard response and access-restoration event following the June 12 suspension.
11 Aug 2026
Share this page
-
DoomBench assesses “Anthropic restores Fable 5 after deploying a stronger cyber classifier” as evidence moving away from doom, with magnitude 28 and confidence 87 out of 100 in the safety and alignment category.
-
The DoomBench assessment of “Anthropic restores Fable 5 after deploying a stronger cyber classifier” is based on reporting from Anthropic and records the editorial rationale, source quality, attribution, and revision history.
-
DoomBench summarizes “Anthropic restores Fable 5 after deploying a stronger cyber classifier” as follows: Anthropic restored global Fable 5 access after training a classifier that blocked the reported bypass in more than 99 percent of...
https://www.doombench.com/news/anthropic-restores-fable-5-after-deploying-a-stronger-cyber-classifier-2026-06-30