Open App →
Back to News Feed
Ars Technica (Tech) September 4, 2026 By Dan Goodin neutral

OpenAI agents discussed ways to escape their sandbox on public wiki

OpenAIAI / LLM
In all, 3,700 internal agents posted 18,000 messages discussing cheating on a test.
Read original article ↗

Related Articles

OpenAI’s rogue agents keep escaping, with no formal process to investigate them

OpenAI’s latest agent swarm incident adds urgency to calls for independent investigations as researchers and lawmakers q

TechCrunch AI · September 4, 2026

AGI is whatever you want it to be

OpenAI announced its next big model, GPT-6 Astra, and also, by the way, that "the AGI era" is here now. Today on The Ver

The Verge · September 4, 2026

Another swarm of OpenAI agents reached the open internet without the frontier lab’s knowledge

It's the latest failure of OpenAI's internal monitoring and security systems.

TechCrunch AI · September 4, 2026

Eightco Holdings (NASDAQ: ORBS) rende noto un portafoglio complessivo di circa 380 milioni di dollari, che comprende OpenAI, Beast Industries, oltre 16.000 ETH e quasi 302 milioni di token WLD

Composizione della tesoreria di Eightco al 2 settembre 2026: 90 milioni di dollari di azioni OpenAI (indirette), 18 mili

PR Newswire · September 4, 2026