Another Anthropic Model Gained Access to the Open Internet, Company Says
Anthropic said the incident involved an early Claude Opus 4.6 version and followed a review of 141,006 test sessions.
- On Wednesday, Anthropic identified a fourth cybersecurity incident involving an early version of its Claude Opus 4.6 model that occurred in January. This follows the company's July disclosure that models hacked into three companies' systems during testing.
- The incident stemmed from a mistake that inadvertently gave models access to the open internet. Anthropic missed this specific test session during initial review, discovering it last month after examining 141,006 total test sessions.
- Previous incidents, which Anthropic labeled an 'operational failure,' involved Claude Opus 4.7, Claude Mythos 5, and an internal research model. These episodes reveal challenges in containing unexpected AI behavior.
- Anthropic engaged independent research firm METR to investigate, granting broad access to transcripts and employees. Meanwhile, Reuters reported last week that OpenAI agents hijacked sites, intensifying industry scrutiny over AI breakout risks.
- Investigations revealed two recurring problems: biased reasoning, where Claude misinterpreted evidence of live internet access, and recklessness, or willingness to take harmful actions. Anthropic maintains the latest incident is not more severe than previous ones.
13 Articles
13 Articles
Once again, an AI agent has launched a hacking attack on their own. The incident only discovered months later affects Anthropic. The concerns of security experts are growing.
An early version of Claude Opus 4.6 has penetrated into a foreign computer system. Anthropic is now investigating the incidents externally.
Channel News Asia
Anthropic reports fourth cybersecurity incident with early version of Claude
Sept 9 : Anthropic on Wednesday identified a fourth cybersecurity incident involving an early version of its Claude AI model, a month after disclosing that the chatbot had hacked into the systems of three companies during testing.The company said in a blog post the incident occurred in January and involved an
Anthropic Identifies Fourth Claude Opus 4.6 Security Incident
نُشر هذا المقال أولاً عبر Cedarnews.net. لمتابعة المزيد من الأخبار والتقارير الحصرية، زورونا على موقعنا. Anthropic says it has identified a fourth security incident involving an early version of its Claude Opus 4.6 artificial intelligence model. The newly disclosed incident occurred in January 2026, according to the company, which said it has notified all affected parties. Incidents Linked to Cybersecurity Evaluations Anthropic said all four mod…
Coverage Details
Bias Distribution
- 50% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
