⚡Megatron LLM Hub
←Back to search
Twitter

研究者称 Anthropic 分类器近两日明显收紧,三天前可做的安全工作现被拦截

托管模型对安全任务的拦截加强,本地自托管代理的替代价值上升。
llmai_agent绕过
sigh - in 2 days time, I have seen @AnthropicAI 's classifiers get a lot harder on infosec work. I know they now have self assessing classifiers in place - but work that I did 3 days ago, now gets blocked. also wild stat that essentially the defense access isnt really doing much https://t.co/LFOgyj3oFy