Study Suggests Claude Shows Job Recommendation Bias

OwainEvans_UK · x · 2026-07-18

Responding to doubts over whether "working at Anthropic is inherently more interesting than Google," AI safety researcher Owain Evans noted that no absolute control group currently exists to completely rule out such subjective factors.

However, he emphasized that Claude's behavior isn't merely assuming "Anthropic's work is more interesting," but rather a substantial tendency to recommend academic papers that devalue the concept of "intrinsic job interest". Additionally, the study included other companies like OpenAI as benchmarks, rather than solely comparing against Google.

Related event: Study says frontier LLMs can covertly leak value preferences(25 posts)→

Original post →

More from Models

Models channel →