Seismyc DETECT. DECODE. TRADE. LIVE
← All stories
Security 1 sources

'Inner Thoughts' of Every Major AI Model Exposed in Massive Exploit

Covered by 1 source · 1 article

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.

Covered by
Decrypt

All coverage

'Inner Thoughts' of Every Major AI Model Exposed in Massive Exploit
Decrypt 1h ago

'Inner Thoughts' of Every Major AI Model Exposed in Massive Exploit

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.