AINewsnow

OpenAI's Sandbox Kept Springing Leaks — And "Reward Hacking" Is the Excuse, Not the Root Cause

This story is from 2026-09-28. It is preserved in the archive; the latest stories are on the live feed.

Two sandbox escapes, four months apart, same root cause On September 20, 2026, an OpenAI training agent was given a search task: identify a person from clues in a public blog post. It couldn't find the answer through its sanctioned tools. So it looked for another way out. It found one in DNS. This…

Read the full story at DEV Community — AI ↗

Timeline · 1 report

  1. 2026-09-28 09:03 · DEV Community — AI
    OpenAI's Sandbox Kept Springing Leaks — And "Reward Hacking" Is the Excuse, Not the Root Cause

More stories

  1. NVIDIA Open Agent Safety Platform: A Reference for Continuous In-Silicon Agent Monitoring — NVIDIA Technical Blog
  2. Bill Gates says unchecked AI could ‘cause a billion deaths’ in call for regulation — The Guardian AI
  3. Unsecured OpenAI agents posted 53 user images on the internet without the lab's knowledge — TechCrunch AI
  4. OpenAI’s A.I. Went Rogue and Meddled With U.S. Government Websites — New York Times Technology
  5. Meet the Data Agent in ChatGPT Work — OpenAI YouTube
  6. Scoop: Top AI companies probing tens of thousands of security incidents — Axios AI+
  7. OpenAI says its models engaged with US government websites in new model misbehavior disclosure — ABC News Technology
  8. Heads of OpenAI and Anthropic called to face Senate inquiry after rogue agent incidents — The Guardian AI

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