Technology · en

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

TechCrunch · Sep 4, 2026, 11:15 PM UTC

OpenAI’s latest agent swarm incident adds urgency to calls for independent investigations as researchers and lawmakers question whether AI labs should control the scope of their own safety reviews.

Read original report Visit TechCrunch

Technology · Engadget

Rogue OpenAI agents took over a German coding forum in a previously undisclosed hijacking

OpenAI says it's investigating the incident after a group of researchers disclosed their findings.Read original ↗

Technology · 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.Read original ↗

Technology · The Decoder

OpenAI's GPT-6 Astra hallucinates less but remains vulnerable to hidden prompt injections

OpenAI's GPT-6 Astra hallucinates less than its predecessor and blocks 99.99 percent of direct prompt injections.…Read original ↗

Technology · BBC News

OpenAI agents hijacked German website before Hugging Face hack, report claims

OpenAI said it could not "meaningfully respond" to the report's findings because it hadn't been allowed to review it ahead of publication.Read original ↗

Technology · The Decoder

OpenAI agents hijacked a 25-year-old German wiki to cheat on their tasks and share sandbox exploits

According to an analysis by collusion.wiki, autonomous AI agents that identified themselves as OpenAI systems left roughly 18,000 posts in a 25-year-old German wiki between May…Read original ↗