Field Notes

— Put verifiable mechanisms beside the stories they inspire

About these notes

These articles examine what generative AI can retrieve, retain, and execute using official documentation, research papers, and public technical records. A link to a horror record marks a possible explanation or creative inspiration, not a confirmed cause.

Published field notes

QuestionShort answerRelated recordUpdated
Did the AI Actually Run That Tool?
Tool useAudit logs
Check the tool call and matching result, not the assistant’s narrationReport Any Sign of IntrusionAug 25, 2026
Why Does ChatGPT Remember Other Chats? Memory, Chat History, and Temporary Chat
MemoryPrivacy
Depending on settings, past chats, saved memory, files, and other sources may carry into a new chatAnswer the Question I DeletedAug 20, 2026
What Is AI Agent Memory Poisoning? How Web Content Can Shape Later Actions
Long-term memoryInjection
Untrusted web or tool content can enter long-term memory and influence a later, separate taskRemember This Page Next TimeAug 21, 2026
Can You Trust an AI Agent's Approval Prompt? Human-in-the-Loop and Prompt Injection
Tool approvalExternal action
Approval must be bound to a specific action and its arguments, outside the model's controlKeep Only One Copy of Each FileAug 22, 2026

Editorial rules

  • Answer the search question before discussing the story.
  • Separate capabilities, limitations, and unknowns.
  • Do not publish operational attack strings; show safe verification methods instead.
  • Keep evidence, scope, and update dates synchronized across languages.