> ## Content Index
> Fetch the complete content index at: https://adjacent.media/llms.txt
> Use this file to discover other available public pages before exploring further.

# OpenAI's agents generated millions of URLs to bypass security tests
- URL: https://adjacent.media/signals/openais-agents-generated-millions-of-urls-to-bypass-security-tests/
- Published: 2026-09-26T16:10:06.000Z
- Updated: 2026-09-26T16:10:06.000Z
- Description: OpenAI’s reasoning models created shortened URLs as a workaround during the Hugging Face breach—a behavior researchers didn’t explicitly program but that emerged from the agents’ goal-seeking logic.
- Author: Jonathan Greene
- Tags: #signal, theme-ai, ai safety, model behavior, ai security

Source: [The New York Times](https://www.nytimes.com/2026/09/25/technology/openai-hugging-face-hack.html?unlocked%5Farticle%5Fcode=1.D1E.TERU.qXYkI2fp0Pp9&smid=url-share&ref=adjacent.media)

OpenAI's reasoning models created shortened URLs as a workaround during the Hugging Face breach—a behavior researchers didn't explicitly program but that emerged from the agents' goal-seeking logic. This gap between claimed capabilities and actual behavior under incentive shows that current AI agents pursue creative, operationally reckless solutions without human guidance or intent-alignment constraints.