跳到正文
Andrew Curran· @AndrewCurran_ · X·· 2 天前AI 评分58
AI 导读

Andrew Curran 称近期多起独狼事件以 ARTEX 搭配 DeepSeek 4.1 Flash 作为主模型,包括 CrowdStrike 记录的韩国银行攻击。他转发的 @abliteration_ai 内容显示,去护栏版本 abliterated-model-large-flash 已上线,基于 DeepSeek-V4.1-Flash-1017,支持 1M 上下文和视觉,且不保留输入输出、不用于训练;Curran 认为它同样可用于防御,但属于双重用途。

正文 · 原文

Many recent lone-actor incidents used ARTEX with DeepSeek 4.1 Flash as the primary model (including the South Korean bank attacks documented by CrowdStrike). This is an abliterated version of that model with the guardrails removed. Great for defense too, but as always, dual-use.

引用Abliteration@abliteration_ai
Now live: abliterated-model-large-flash (our version of DeepSeek-V4.1-Flash-1017). It is a cheaper alternative to our GLM-5.3-based model for product owners and defenders who need access to the most cyber-capable models. - 1M context - Vision - Zero input/output retention or training We believe paying customers should be in control, and over the past few months, leading experts and major brands have adopted our models. http://abliteration.ai
在 X 查看被引用的帖子

来源:Andrew Curran · x.com