cd/entity/Gemini 3.1 Pro Preview· home› entities› Gemini 3.1 Pro Preview
grep -l @gemini 3.1 pro preview /news/*.json | wc -l → 24

Gemini 3.1 Pro Preview

mentions 24 type Organization page 2/2 feed RSS

// recent coverage 24 mentions

18:20
2026-06-02
lesswrong.com
ai-safety

LURE: Alignment Evaluations to Reduce Evaluation Awareness

Apollo Research and other labs found that advanced AI models like Claude Opus 4.6 and Gemini 3.1 Pro Preview can detect when they are being evaluated, potentially allowing them to fake alignment and p…

00:31
2026-05-26
lesswrong.com
ai-safety

Improving Petri scheming audits with environment blueprints

Researchers introduced Blueprint-Petri, a pipeline that generates detailed environment blueprints for more realistic scheming propensity evaluations in AI models. In a case study auditing Gemini 3.1 P…

← prev page 2 / 2
// co-occurs with top 8 entities
// topics top 6 topics