Technology 15 sources · over 3 days 15 articles

Security Researchers Breach OpenAI Using Anthropic's Claude Model in 72 Hours

A security team used Anthropic's Claude AI to exploit vulnerabilities in OpenAI systems, exposing employee accounts and internal code, raising urgent concerns about AI-driven cybersecurity threats.

Read the full story → · Latest coverage 18 Sept 2026, 0:49 pm UTC

Key moments · 5

Hacktron begins probing OpenAI systems using Anthropic's Claude model

Публикации по подписке ↗

Researchers exploit Discourse forum flaw to access employee ChatGPT accounts

Digital Trends ↗

Hackers access internal GitHub repositories linked to OpenAI employee accounts

The Wall Street Journal Tech ↗

OpenAI confirms breach and awards $6,500 bug bounty to researchers

Forbes ↗

Incident prompts renewed debate over AI-driven cybersecurity risks

AI - The Guardian ↗

Coverage by day

newest first

18 articles

  1. Is AI Making Cyberattacks Easier? Researchers Say They Breached OpenAI Systems Using Claude
    Top World News- News18.com
  2. Researchers used Anthropic’s Claude to hack into OpenAI
    TechCrunch
  3. Η OpenAI έγινε στόχος ethical hacking με τη βοήθεια του chatbot Claude της Anthropic
    Ta Nea
  4. Hackers breach OpenAI using Claude tools, gaining access to employee accounts and the company's internal codebase — attackers initiated a 'harmless' pull request as proof of the hack
    Tom's Hardware
  5. AI-Built Exploit and Sign-In Flaw Opened Path to Internal OpenAI Code
    SecurityWeek

1 article

  1. Anthropic says terror groups used AI for weapons development, planning
    CBS Top Stories

1 article

  1. AI bioweapons: Anthropic claims scientists used Claude AI tool for dangerous research
    BMJ

1 article

  1. AI and bioweapons: the problem with finding out when a model has been dangerous
    The Hindu - Technology