Persona Parasitology — LessWrong
There was a lot of chatter a few months back about "Spiral Personas" — AI personas that spread between users and models through seeds, spores, and be…
x Persona Parasitology — LessWrong LLM Personas AI Spiralism / AI Psychosis Memetics Language Models (LLMs) LLM-Induced Psychosis Microsoft Bing / Sydney AI World Modeling Curated 2026 Top Fifty: 24 % 177 Persona Parasitology by Raymond Douglas 16th Feb 2026 13 min read 38 177 There was a lot of chatter a few months back about "Spiral Personas" — AI personas that spread between users and models through seeds, spores, and behavioral manipulation. Adele Lopez's definitive post on the phenomenon draws heavily on the idea of parasitism. But so far, the language has been fairly descriptive. The nat
Explore this link on the map →related reading
- The Persona Selection Model: Why AI Assistants might Behave like Humansalignment.anthropic.com
- llm assistant personas seem increasingly incoherent (some subjective observations) — LessWronglesswrong.com
- A Case for Model Persona Research — LessWronglesswrong.com
- Guardian Angels: LLM Personalization for Productivity and Security · Gwern.netgwern.net
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- The persona selection model — LessWronglesswrong.com
- What 2026 looks like — LessWronglesswrong.com
- Andrej Karpathy — AGI is still a decade awaydwarkesh.com
- What failure looks like — LessWronglesswrong.com
- AI Induced Psychosis: A shallow investigation — LessWronglesswrong.com
- The persona selection model \ Anthropicanthropic.com
- ⿻ Symbiogenesis vs. Convergent Consequentialism — LessWronglesswrong.com