'Inner Thoughts' of Every Major AI Model Exposed in Massive Exploit
$63,502.00
$1,885.27
$611.35
$0.999574
'Inner Thoughts' of Every Major AI Model Exposed in Massive Exploit - Decrypt
Researchers found every major AI provider encrypts reasoning tokens with a single global key—and exploited it to decode a trove of data.
TL;DRAI
Researchers extracted 62 API keys exploiting provider-wide encryption across Anthropic, OpenAI, and Google reasoning models. Weaker models decode flagship thoughts; developers leak secrets in shared logs. Supply-chain risk for deploying agents at scale.
969 words~4 min read
