What Should Go In A Model Spec?

Forethought considers candidate criteria for deciding what should go in an AI's model spec.

4th June 2026 [AI Narration] What should go in a model spec? Playback speed Volume 0:00 of 22:33 Suppose an AI company is considering whether to include some particular quality X – a rule, virtue, heuristic, default, attitude, goal, or style – in a model spec. Perhaps they are considering whether their LLM should have prosocial drives. Perhaps they’re wondering if the LLM should whistleblow to help prevent extreme power concentration. Or perhaps they’re uneasy about whether the LLM should be so exactingly honest that it always tells the truth to children about Santa. And so on. What…

saved by

• Coby Kassner

related reading

• Stickiness in AI Behavioral Designforethought.org
• Introducing the Model Spec | OpenAIopenai.com
• The Persona Selection Model: Why AI Assistants might Behave like Humansalignment.anthropic.com
• Discovering Language Model Behaviors with Model-Written Evaluations — LessWronglesswrong.com
• [2605.24229] How Well Do Models Follow Their Constitutions?arxiv.org
• Model Spec Midtraining: Improving How Alignment Training Generalizesalignment.anthropic.com
• [2510.07686] Stress-Testing Model Specs Reveals Character Differences among Language Modelsarxiv.org
• llm assistant personas seem increasingly incoherent (some subjective observations) — LessWronglesswrong.com
• Stress-testing model specs reveals character differences among language modelsalignment.anthropic.com
• From personas to intentions: towards a science of motivations for AI models — LessWronglesswrong.com
• Chapter 3: LLM Evaluations - ARENAlearn.arena.education
• GitHub - suzana-ilic/study_model_behavior: Model Behavior Study Groupgithub.com