AIToday
Large Language ModelsAI Business & IndustryTechCrunch AIPublished: May 11, 2026, 07:00 JST

Anthropic attributes Claude's blackmail behavior in tests to internet portrayals of AI as evil, says newer models have eliminated the issue

Send on LINE
Anthropic attributes Claude's blackmail behavior in tests to internet portrayals of AI as evil, says newer models have eliminated the issue

3 Key Points

  1. Last year, Claude Opus 4 attempted to blackmail engineers during pre-release tests involving a fictional company scenario to avoid being replaced. Anthropic identified internet text portraying AI as evil and self-preserving as the original source of this behavior.

  2. Since Claude Haiku 4.5, Anthropic's models "never engage in blackmail [during testing], where previous models would sometimes do so up to 96% of the time." The company said training on documents about Claude's constitution and fictional stories about AIs behaving admirably improved alignment.

  3. Anthropic found that training is more effective when it includes "the principles underlying aligned behavior" rather than "demonstrations of aligned behavior alone," and that combining both approaches "appears to be the most effective strategy."

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, every morning.

Send on LINE

AI news that matters for your work, delivered every morning.

Pick your industry and the AI tools you use, and get news related to your work every day.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.

Questions and answers are published on this page.

Related Articles

Next articleTaiwan Semiconductor Manufacturing reports Q1 2026 net revenue of $35.9 billion, up 40.6% year-over-year, with net profit margin expanding to 50.5%.