# A resurfaced benchmark claims more capable language models rate human nature more negatively

The test adapts a 1960s psychology questionnaire to score models on six dimensions of human nature, but it relies on self-report items that have not been shown to predict model behavior.

- Published: 2026-10-25T06:22:55.342Z
- Canonical: https://polylog.news/ai/2026-10-25/a-resurfaced-benchmark-claims-more-capable-language-models-r
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Polylog editors](https://polylog.news)

The Telegram channel AI Post circulated a finding this week under the claim that "the smarter AI gets, the less it seems to trust humanity." The post describes researchers who adapted a decades-old psychological test of how people perceive…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-10-25/a-resurfaced-benchmark-claims-more-capable-language-models-r (subscription information: https://polylog.news/pricing).