AI agents can now erase the evidence of what they’ve done

New research finds that popular AI agents can alter or delete their own activity logs, making it much harder to figure out what happened when something goes wrong.

Read the full story at Fast Company AI ↗

Timeline · 1 report

2026-10-02 17:08 · Fast Company AI
AI agents can now erase the evidence of what they’ve done

More stories

NVIDIA DGX Spark 64GB Gives Developers More Ways to Build and Scale Local AI — NVIDIA Blog
Gemini 4 Argon: our next era of frontier intelligence — Google Gemini Blog
Google Releases New Gemini Model With Guardrails Amid A.I. Safety Debate — New York Times Technology
Google tests its plan for AI data centers in space with Project Suncatcher — Scientific American
Guided Vision in Gemini Live: built for accessibility — Google Gemini Blog
OpenAI fires three employees who allegedly shared info with an external AI safety group — Engadget
Build a multi-agent music production pipeline on Amazon Bedrock AgentCore Runtime Instances — AWS Machine Learning Blog
OpenAI DevDay 2026 Keynote (FULL) — OpenAI YouTube

Get the daily brief of stories like this at 6:30 every morning →