'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.
- Source
- Decrypt
- Published
- 2026-08-12 20:31 UTC
- Cache updated
- 2026-08-12 20:34 UTC
This page shows only the title, summary, and source metadata. Read the full story at the original source.
Open original ↗Check transfer feesRelated topics
01Users and Apps02On-chain Security
Decrypt
Follow consumer wallet, application, security, DeFi, and market updates before deciding whether Energy rental is needed.
On-chain Security, Phishing, and Wallet Risk News
Follow security alerts, phishing reports, malicious addresses, and wallet-risk updates before connecting wallets or copying addresses.