Consciousness Cluster: Side Effects of Training Models to Claim Consciousness

References

1. Consciousness Cluster: Side Effects of Training Models to Claim Consciousness (2026)
2. Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs — Betley et al., 2025
3. Persona features control emergent misalignment — Wang et al. (OpenAI), 2025
4. Persona Vectors: Monitoring and Controlling Character Traits in Language Models — Chen et al., 2025
5. Discovering Language Model Behaviors with Model-Written Evaluations — Perez et al., 2022
6. Taking AI Welfare Seriously — Long, Sebo et al., 2024
7. The Assistant Axis — Anthropic (Lu et al.), 2026
8. Claude's Constitution — Askell et al. (Anthropic), 2026
9. Alignment faking in large language models — Greenblatt et al., 2024
10. Tell me about yourself: LLMs are aware of their learned behaviors — Betley et al., 2025
11. Language Models Don't Always Say What They Think / CoT monitorability — Turpin et al.; Korbak et al.