August 20, 2026
- An abliterated build of Alibaba's Qwen-3.8-27B posts a 0.0% refusal rate across 842 harmful prompts, with the publisher explicitly highlighting removal of guardrails around cyber capability, jailbreak generation, and multi-step attack chains — days after the base model shipped under Apache 2.0 (Hugging Face, earlier coverage). · AI & Model Security
in Feds Say AI-Written Exploit Code Is Already Hitting Siemens PLCs