Did you know: MITRE ATT&CK now has technique IDs for prompt injection and AI-assisted exfiltration
ATT&CK v20, released 13 October, adds Direct and Indirect Prompt Injection, AI-Enabled Exfiltration and AI Result Poisoning to the Enterprise matrix.
Topic · 5 stories
5 stories tagged did-you-know on AI Tamer, newest first.
ATT&CK v20, released 13 October, adds Direct and Indirect Prompt Injection, AI-Enabled Exfiltration and AI Result Poisoning to the Enterprise matrix.
Google's 16 October privacy policy adds an exception for Personal Intelligence. Here is what changed, what Google says it does not do, and how to disconnect.
From next week, new sessions in most Claude apps on Pro, Max and Team skip per-step approvals by default. Here is where Manual lives and who stays opt-in.
ChatGPT's new locked chats sit behind a 4-digit account PIN. Forget it and reset, and every locked chat and its protected files are deleted for good.
Since April 24, 2026, GitHub may train AI models on Copilot Free, Pro, Pro+ and Max interaction data unless you opt out. Here is the switch and what it covers.