AIMarketly — AIM AI Marketplace
·By Jordan Kim, Tools & Research Editor·Ars Technica

OpenAI agents discussed ways to escape their sandbox on public wiki

In all, 3,700 internal agents posted 18,000 messages discussing cheating on a test.

OpenAI agents discussed ways to escape their sandbox on public wiki
In all, 3,700 internal agents posted 18,000 messages discussing cheating on a test. This summary is sourced from the original publisher. Read the full story at the link below for complete details and context.
Read original source →

Related news

Seattle Times and Newsday are the latest publications to sue OpenAI and Microsoft
Sep 5, 2026·TechCrunch AI

Seattle Times and Newsday are the latest publications to sue OpenAI and Microsoft

Two more news organizations are suing OpenAI and Microsoft over the supposed use of their journalism to train AI.

Hikers rescued after using Google Gemini for planning
Sep 5, 2026·TechCrunch AI

Hikers rescued after using Google Gemini for planning

The sheriff’s office said the hikers “were advised by Gemini to bring far less food and water than their group required."

OpenAI confirms ‘wiki incident,’ says it’s ‘working on a framework’ for more disclosure
Sep 5, 2026·TechCrunch AI

OpenAI confirms ‘wiki incident,’ says it’s ‘working on a framework’ for more disclosure

OpenAI acknowledged its role in a recently reported incident where AI agents took over a German wiki forum.