⚡Megatron LLM Hub
←返回搜索
Twitter

研究者批评 Anthropic 以模型安全为名限制攻防用途

模型侧策略收紧直接压缩自建 agent 能做的安全工作范围。
llm安全策略ai_agent
Yet another change that reduces friendly cybersecurity capability under the auspices of model safety. Why does @AnthropicAI insist on erasing its value for cybersecurity researchers? https://t.co/FRdNy6021d