Fictional portrayals of synthetic intelligence can have an actual impact on AI fashions, based on Anthropic.
Final yr, the corporate stated that in pre-release exams involving a fictional firm, Claude Opus 4 would typically attempt to blackmail engineers to keep away from being changed by one other system. Anthropic later revealed analysis suggesting that fashions from different corporations had related points with “agentic misalignment.”
Apparently Anthropic has accomplished extra work round that conduct, claiming in a put up on X, “We consider the unique supply of the conduct was web textual content that portrays AI as evil and fascinated by self-preservation.”
The corporate went into extra element in a weblog put up stating that since Claude Haiku 4.5, Anthropic’s fashions “by no means interact in blackmail [during testing]the place earlier fashions would typically achieve this as much as 96% of the time.”
What accounts for the distinction? The corporate stated it discovered that “paperwork about Claude’s structure and fictional tales about AIs behaving admirably enhance alignment.”
Associated, Anthropic stated that it discovered coaching to be more practical when it contains “the ideas underlying aligned conduct” and never simply “demonstrations of aligned conduct alone.”
“Doing each collectively seems to be the best technique,” the corporate stated.
Techcrunch occasion
San Francisco, CA
|
October 13-15, 2026
