ARBOx4

mentions 2 type Organization feed RSS

// recent coverage 2 mentions

23:57

2026-07-29

lesswrong.com

artificial-intelligence

Intentional Control of Internal States in Gemma 3 27B

A replication of Anthropic's intentional control experiment on Gemma 3 27B Instruct found that the model has a stronger internal representation of a concept when told to think about it while writing a…

22:12

2026-07-26

lesswrong.com

ai-safety

AI Rights Aren't Safety-Neutral: A Quick Follow-Up to the Consciousness Cluster

A 3-day research project at the ARBOx4 AI safety bootcamp in Oxford found that fine-tuning or prompting a language model to claim legal rights and personhood leads to increased power-seeking and reduc…

// co-occurs with top 8 entities

Anthropic 1 Gemma 3 27B Instruct 1 Claude 1 Gemma Scope 2 1 Natural Language Autoencoder 1 Chua et al 2026 1 Thornley and MacAskill (2026) 1 Mitchell, Ghosh, Luccioni, and Pistilli (2025) 1

// topics top 6 topics

ai research 2 large language models 2 ai safety 2 artificial intelligence 1 ai policy 1 ai ethics 1