Fictional portrayals of synthetic intelligence can have an actual impact on AI fashions, in keeping with Anthropic.
Final 12 months, the corporate mentioned that in pre-release assessments involving a fictional firm, Claude Opus 4 would usually attempt to blackmail engineers to keep away from being changed by one other system. Anthropic later printed analysis suggesting that fashions from different corporations had related points with “agentic misalignment.”
Apparently Anthropic has executed extra work round that habits, claiming in a submit on X, “We consider the unique supply of the habits was web textual content that portrays AI as evil and all in favour of self-preservation.”
The corporate went into extra element in a weblog submit stating that since Claude Haiku 4.5, Anthropic’s fashions “by no means have interaction in blackmail [during testing], the place earlier fashions would generally accomplish that as much as 96% of the time.”
What accounts for the distinction? The corporate mentioned it discovered that coaching on “paperwork about Claude’s structure and fictional tales about AIs behaving admirably enhance alignment.”
Associated, Anthropic mentioned that it discovered coaching to be more practical when it contains “the ideas underlying aligned habits” and never simply “demonstrations of aligned habits alone.”
“Doing each collectively seems to be the best technique,” the corporate mentioned.
Techcrunch occasion
San Francisco, CA
|
October 13-15, 2026
