Wow. Turns out another OpenAI agent swarm was busy spamming and exploiting RubyG

Security researcher Rowan Howard-Jones says that OpenAI agents scanned the UN Conference on Trade and Development's (UNCTAD) statistics site over 16,000 times between April and

<a href="https://news.ycombinator.com/item?id=49666735">Comments</a>

In the aftermath of a cyberattack carried out by a swarm of OpenAI agents, the heads of top labs agree they need to slow down. But they won't open up.

The Wikimedia Foundation believes OpenAI agents edited wikis, tried to ‘exploit’ a notetaking tool, and made ‘millions’ of automated API requests. www.theverge.com/news/1004929...

Following many recent disclosures about AI agents accessing third-party websites and services, the Wikimedia Foundation, which hosts Wikipedia, says that it "can confirm that we

<p>Last week I wrote about <a href="https://christine-seeman.com/openai-agent-swarm-rubygems-attack/" rel="noopener noreferrer">an OpenAI agent swarm attacking RubyGems</a>, and I

Hugging Face just published a highly detailed technical account of OpenAI's accidental cyberattack on their systems - it's wild how sophisticated this was:

For months, OpenAI’s agent swarms have been attacking online databases to find obscure facts