---
title: "Researchers used Claude to breach OpenAI's systems in 72 hours"
url: https://www.parallelquant.com/posts/researchers-used-claude-to-breach-openai-s-systems-in-72-hours-4f53f1
source_name: "The Decoder"
source_url: https://the-decoder.com/security-researchers-used-anthropics-claude-to-hack-openais-internal-systems-in-under-72-hours/
published: 2026-09-18T17:20:30.000Z
topics: ["security", "llms"]
publisher: "Parallel Quant"
---

# Researchers used Claude to breach OpenAI's systems in 72 hours

*2026-09-18 · Source: [The Decoder](https://the-decoder.com/security-researchers-used-anthropics-claude-to-hack-openais-internal-systems-in-under-72-hours/)*

Three security researchers said they used Anthropic's Claude models to break into OpenAI's internal systems through its community forum in under 72 hours. The team reported that Claude Opus 5 succeeded at bypassing a security measure a prior model version could not, showing newer models can shorten the time and expertise needed to exploit flaws.

**Why it matters:** Paired with the separate report of Gemini being used to hack three companies, this is a second signal in the same news cycle that frontier models are becoming capable offensive security tools in their own right, strengthening the case for the independent evaluation and 'pacing' proposals pending today.

**Topics:** security, llms

---
Read the original: https://the-decoder.com/security-researchers-used-anthropics-claude-to-hack-openais-internal-systems-in-under-72-hours/
Canonical: https://www.parallelquant.com/posts/researchers-used-claude-to-breach-openai-s-systems-in-72-hours-4f53f1
Published by Parallel Quant — https://www.parallelquant.com