← Back to KHAO

Anthropic · OpenAI · Claude · Google · GitHub · The Information ·

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

2 min read

Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.

★ Tier-1 Source

Source: Decrypt.

Security researchers have found a way to read the encrypted "inner thoughts" of every major AI reasoning model—and uncovered 62 live API keys and 33 passwords buried in session logs that developers had shared publicly online without knowing what was inside them.

Key facts

Summary

A team or researchers found that Anthropic, OpenAI, and Google all use a single global encryption key for AI reasoning tokens. By decoding 315,320 reasoning blocks scraped from public GitHub and Hugging Face repositories, the researchers recovered 182 credentials, including 62 live API keys, 33 passwords, and 30 personal email addresses. OpenAI, Anthropic, and Google deployed server-side patches after responsible disclosure, but historical session logs already shared publicly remain decodable. “By decoding 315,320 reasoning blocks scraped from public repositories, we recovered 367 Personally Identifiable Information (PII) artifacts and 182 credentials,” the researchers wrote.

Read full article at Decrypt →

#Anthropic #OpenAI #Claude #Google #GitHub #The Information