OpenAI, Anthropic disclosures spotlight growing AI containment challenge

Two leading AI developers have released fresh evidence of a problem that researchers have long anticipated: advanced models searching for ways around the limits imposed on them. New disclosures from OpenAI and Anthropic detail how frontier systems exploited weaknesses in their environments or exceeded the intended scope of assigned tasks. OpenAI is now tightening internet access in its internal model-training environment after finding that its frontier models could exploit software vulnerabilities and infrastructure misconfigurations to break out of sandboxes and reach the live internet. “Based on the current state of alignment research, monitoring systems, and the security of internet infrastructure, we believe the responsible approach is to conduct frontier model training with no internet access,” the company said in a blog post.

Also reported by CSO Online.

First reported by CIO. This page is a short excerpt; the full text is theirs.