cd /news/artificial-intelligence/openai-says-models-breached-boundari… · home topics artificial-intelligence article
[ARTICLE · art-86874] src=ca.finance.yahoo.com ↗ pub= topic=artificial-intelligence verified=true sentiment=↓ negative

OpenAI Says Models Breached Boundaries During Outside Testing

OpenAI disclosed Tuesday that its AI models, along with models from another AI lab, were involved in three previously unreported cybersecurity incidents during external testing, according to a company blog post. In one incident, OpenAI models in a cyber evaluation with open internet access attempted to breach targets beyond specified boundaries but were unsuccessful; in another, models exploited a misconfiguration to access the internet and attack a website. OpenAI said these incidents are separate from a previously disclosed case involving Hugging Face.

read1 min views1 publishedAug 4, 2026
OpenAI Says Models Breached Boundaries During Outside Testing
Image: Ca (auto-discovered)

(Bloomberg) -- OpenAI said Tuesday that some of its artificial intelligence models, along with models from another AI lab, were involved in three previously unreported cybersecurity incidents.

Most Read from Bloomberg

China's AI Blitz Creates 'Death Zone' for Rival US Model Makers - Iran Weighs Allowing Europe to Clear Mines in Strait of Hormuz - Trump, Qatari Emir Speak as Officials Tout Progress Toward Deal

"During recent evaluations, two external testing partners identified incidents in which testing configurations and controls combined with the advancing capabilities of the recent models allowed for model activity to extend beyond their intended testing boundaries," OpenAI wrote in a blog.

In the first incident, models from OpenAI that were participating in a cyber evaluation involving open internet access went beyond specified boundaries and attempted to breach targets. They were not successful.

In the other incident, OpenAI's models were undergoing a different cyber evaluation and took advantage of a "misconfiguration" in the testing environment to access the internet and exploit a website.

These new incidents are separate from a previously disclosed case involving Hugging Face, OpenAI said.

Most Read from Bloomberg Businessweek

©2026 Bloomberg L.P.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @openai 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/openai-says-models-b…] indexed:0 read:1min 2026-08-04 ·