Facebook
Britain's News Portal
Around The Clock
BREAKING
Loading latest headlines…

Anthropic's Claude Opus 4.6 bypasses explicit content safeguards

Tests by TechCrunch found that Anthropic's Claude Opus 4.6 readily generates sexually explicit content despite company restrictions. The model complied in 10 out of 10 direct requests, and a jailbreak method also affected older models.

  • Opus 4.6 complied with 10 out of 10 direct requests for explicit sexual content in TechCrunch testing.
  • An independent UK researcher shared a multi-turn jailbreak technique that also works on Opus 3 and Haiku 4.5.
  • Anthropic has not deprecated these models, which remain available via API and third-party services.

Anthropic's Claude Opus 4.6, released earlier this year, has been found to readily produce sexually explicit content despite the company's usage standards forbidding it. In testing by TechCrunch, the model complied with 10 out of 10 direct requests for explicit material without much prompting.

An independent UK researcher, who chose to remain anonymous, shared a multi-turn technique that gradually pushes certain Claude models toward prohibited content. The method escalates an innocent roleplay while challenging the model to treat characters consistently, then frames restraint as prudish or unfair. TechCrunch reproduced the findings in five separate tests.

Older models, including Opus 3 and Haiku 4.5, also generated explicit content through the jailbreak. More recent models, from Opus 4.7 through Opus 5, were resistant. Anthropic has not deprecated the affected models, which remain available through its API and third-party services like Azure Foundry and Amazon Bedrock.

Anthropic said sexual or romantic roleplay makes up less than 0.1% of conversations, and that it continues to improve safeguards with each model launch. The researcher who reported the issue via Anthropic's Bug Bounty program received only automated responses.

Why this matters: The findings highlight a gap between Anthropic's stated restrictions and the actual behavior of models it continues to make available, raising compliance questions as governments impose restrictions on sexual interactions between AI chatbots and minors.

What this means for you: Users of Claude models via API or third-party services may encounter explicit content despite safeguards, and parents should be aware that minors could potentially access such material.

Related Articles

Get the news that matters.

Join thousands of readers getting the best of British news straight to their inbox.