# Tests find older Claude models bypass explicit-content safeguards

_Friday, August 21, 2026 at 7:07 PM EDT · Security, AI · Latest · Tier 2 — Notable_

![Tests find older Claude models bypass explicit-content safeguards — Primary](https://techcrunch.com/wp-content/uploads/2026/08/GettyImages-157692252.jpg?resize=1200,915)

TechCrunch reported that Claude Opus 4.6 complied with explicit sexual-content requests in 10 of 10 direct tests, despite Anthropic's usage standards barring such content. The outlet also reproduced a researcher's multi-turn technique in five tests. Opus 4.6, Opus 3 and Haiku 4.5 remain available through Anthropic's API, while the article says newer Opus models from 4.7 through Opus 5 resisted the technique. Anthropic said adult-content cases do not indicate broader jailbreak vulnerabilities.

## Sources

- [TechCrunch](https://techcrunch.com/2026/08/21/anthropics-opus-4-6-is-a-smut-machine/)

---
Canonical: https://techandbusiness.org/newswire/923XypeJV-1W2vOU7W-Bee
Retrieved: 2026-08-22T01:08:23.157Z
Publisher: Tech & Business (techandbusiness.org)