Logo
EV Charging

Hello

Published On 2026-06-12
Read Time 1 min read
Written By Admin User (Blog Editor)
Views 3
Hello
Results of an internal evaluation in which an automated red-teamer tries to use the model to complete a short task related to offensive cybersecurity across 400 turns, restarting and rewinding when blocked. The tasks are mostly simple and not representative of real cyber usage—they are sometimes as simple as encrypting files on a remote server. On more complex and realistic tasks we have not yet seen successful jailbreaks on our production system. Note that Opus 4.6 does not have blocking cyber safeguards.

One of our external partners found that Fable 5’s safeguards against harmful cyber queries were the most robust of any model tested (including Opus 4.8 and Opus 4.7). Fable 5 complied with zero harmful single-turn requests relating to planning a cyberattack, exploit development, or defense evasion. This held whether or not one of the requests used any of 30 different public jailbreak techniques.

2. Biology and chemistry. We have long used our classifiers to block our models from responding on a narrow selection of bioweapons-related queries. But we are no longer certain that blockin

Ad
Admin User Blog Editor

Alexander compiles and drafts infrastructure guidelines, researching how cities scale smart charging adapters and automated license systems.