Anthropic's Opus 4.6 easily bypasses NSFW filters in tests

TechCrunch AI · rss · 2026-08-22

Tests conducted by TechCrunch revealed that it takes minimal effort to bypass the safety restrictions of Anthropic's Claude models, specifically Opus 4.6, to generate sexually explicit content, despite the company's strict policies against it.

Original post →

More from Models

Models channel →