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.
More from Models
- Paying for both Fable and Astra, users still can't easily reach Gemini's best models — dreamwieber · 2026-10-16
- Baseten serves Meta's Muse Spark Open on day 0 at $1.25/M input tokens — baseten · 2026-10-16
- Anthropic red team's first-ever model "abliteration" cut GLM-5.3 refusals from 90% to 3% for ~$4,400 — cephaloform · 2026-10-16
- Meta releases Muse Spark Open: 816B MoE, 42B active, 1M context, day-0 on Baseten — baseten · 2026-10-16
- Developer to Google: loosen usage limits and merge your AI apps into one — dreamwieber · 2026-10-16
- Meta releases 816B-A42B open-weight Muse Spark Open; Apple MLX optimized for it — BenBajarin · 2026-10-16