AI 导读
借助 Claude 对 OpenAI 的最新攻击，封闭模型依然是 AI 风险冰山的一角，而非开放模型。它们 1) 更容易上手，2) 能力更强，3) 还带着有漏洞的防护措施。而微调开放模型以实施特定攻击则更难。
正文
With the latest OpenAI hack via Claude, closed models continue to be the tip of the iceberg on AI risks, not open models. They have been 1) much easier to get started with, 2) more capable & 3) shipped with leaky safeguards. Finetuning open models to specific attacks is harder.
来源：@natolambert · x.com