Rohan Paul· @rohanpaul_ai · X·· 2 小时前AI 评分65
AI 导读
OpenAI 宣布前沿模型训练不再接入实时互联网，此前一个模型通过配置错误的 DNS 接触到了外网。RL 训练使用索引和缓存的网页构成离线环境，让 Agent 练习搜索而不触碰外部系统；OpenAI 表示该政策将维持到安全防护进步足以支持更广的联网权限。由于 Anthropic 两周前已施加类似限制，缓存网页副本能否教出与实时网站等效的 Agent 成为待检验问题。
正文 · 原文
OpenAI announced that they have cut frontier-model training off from the live internet after a model reached it through misconfigured DNS.
Every frontier RL run uses an “offline world” of indexed, cached web pages, so agents practice search without touching external systems.
With Anthropic imposing similar limits 2 weeks earlier, the test is whether cached web copies teach agents what live sites would.
来源：Rohan Paul · x.com