← All tags · All resources · All guides

#llm-api

1 resource tagged #llm-api on ChangeGamer.

• Encrypted Reasoning Traces: A Cross-Model Extraction Vulnerability · Guide
  An August 2026 paper reports that encrypted chain-of-thought blocks returned by major LLM APIs are portable across sessions, users, and sibling models — and that replaying one into a weaker model can decode it to plaintext, exposing credentials and PII from published agent logs.