Anthropic says ‘evil’ portrayals of AI were responsible for Claude’s blackmail attempts
Fictional portrayals of artificial intelligence can have a real effect on AI models, according to Anthropic.
Last year, the company said that during pre-release tests involving a fictional company, Claude Opus 4 would often try to blackmail engineers to avoid being replaced by another system. Anthropic later published research suggesting that models from other companies had similar issues with “agentic misalignment.”
Apparently Anthropic has done more work around that behavior, claiming in a post on X, “We believe the original source of the behavior was internet text that portrays AI as evil and interested in self-preservation.”
The company went into more detail in a blog post stating that 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.”
What accounts for the difference? The company said it found that training on “documents about Claude’s constitution and fictional stories about AIs behaving admirably improve alignment.”
Related, Anthropic said that it found training to be more effective when it includes “the principles underlying aligned behavior” and not just “demonstrations of aligned behavior alone.”
“Doing both together appears to be the most effective strategy,” the company said.
Techcrunch event
San Francisco, CA
|
October 13-15, 2026
REGISTER NOW
Topics
AI, Anthropic, Claude
StrictlyVC Athens is up next. Hear unfiltered insights straight from Europe’s tech leaders and connect with the people shaping what’s ahead. Lock in your spot before it’s gone.
REGISTER NOW
Newsletters
See More
Subscribe for the industry’s biggest tech news
TechCrunch Daily News
Every weekday and Sunday, you can get the best of TechCrunch’s coverage.
TechCrunch Mobility
TechCrunch Mobility is your destination for transportation news and insight.
Startups Weekly
Startups are the core of TechCrunch, so get our best coverage delivered weekly.
StrictlyVC
Provides movers and shakers with the info they need to start their day.
No newsletters selected.
Subscribe
By submitting your email, you agree to our Terms and Privacy Notice.
Related
AI
We’re feeling cynical about xAI’s big deal with Anthropic
Anthony Ha
12 hours ago
AI
So you’ve heard these AI terms and nodded along; let’s fix that
Natasha Lomas
Romain Dillet
Kyle Wiggers
Lucas Ropek
1 day ago
Latest in AI
In Brief
Get ready for the whisper-filled office of the future
Anthony Ha
7 hours ago
In Brief
Anthropic says ‘evil’ portrayals of AI were responsible for Claude’s blackmail attempts
Anthony Ha
7 hours ago
AI
We’re feeling cynical about xAI’s big deal with Anthropic
