微信内可能无法直接打开本站。请点右上角 ··· → 在浏览器打开，或复制链接。
'Inner Thoughts' of Every Major AI Model Exposed in Massive Exploit
RSS 官方收录 · 可信分层展示
关键摘要
Researchers found every major AI provider encrypts reasoning tokens with a single global key—and exploited it to decode 315,320 hidden thinking blocks from public logs, recovering passwords and live API keys along the way.
摘要引擎：抽取
正文提要
Researchers found every major AI provider encrypts reasoning tokens with a single global key—and exploited it to decode 315,320 hidden thinking blocks from public logs, recovering passwords and live API keys along the way.
来源：https://decrypt.co/375501/inner-thoughts-every-major-ai-model-exposed-exploit