資料來源#
摘要#
實體。 「Model Spec Midtraining: Improving How Alignment Training Generalizes」（arXiv 2605.02087，2026 年 5 月）的第一作者。Anthropic Fellows Program 成員。設計了 MSM 規格，提出並設計實驗，產出所有結果，撰寫論文。
貢獻#
根據 MSM 論文附錄 A 的作者貢獻聲明：
- 主導整個專案
- 設計所使用的 Model Specs（cheese-preference specs、Philosophy Spec、Rules/Value-Augmented/Rule-Augmented specs、General Spec）
- 提出並設計所有實驗
- 產出所有結果
- 撰寫論文
共同作者：Sara Price（Anthropic；指導初始階段）、Jon Kutasov + Samuel Marks（共同指導；Jon 提出專案構想，Sam 引導 controlling-generalization 框架）。
程式碼釋出#
開源了完整的 MSM pipeline、AFT pipeline、Model Specs 及訓練模型：https://github.com/chloeli-15/model_spec_midtraining
相關連結#
- 著作：Model Spec Midtraining (MSM) 論文
- 隸屬：Anthropic（Fellows Program）
- 共同作者：Sara Price、Jon Kutasov、Samuel Marks（Anthropic）
- 相關研究：Synthetic Document Finetuning (SDF)（Wang et al.，MSM 所建構的基礎技術）
- 著作：Model Spec Science（關於哪些 Model Spec 特徵最能泛化的實證研究；她設計了規格與實驗）
資料來源#
Cited by 5
- Model Spec Midtraining (MSM)×2
A new training phase inserted between pretraining and alignment fine-tuning that trains a base…
- Anthropic
Chloe Li — Anthropic Fellows; lead author of Model Spec Midtraining paper
- Entities — People, Orgs, Tools & Projects
Chloe Li — Lead author of MSM paper (arXiv 2605.02087); Anthropic Fellows Program; designed all…
- Model Spec Science
Empirical study of which Model Spec features best generalize alignment; value explanations > rules alone, specific > ge…
- Synthetic Document Finetuning (SDF)
Wang et al. 2025 technique for modifying model beliefs via fine-tuning on synthetic documents; foundation that [[model-…
Related articles
- Claude's Constitution / Model Spec
Anthropic Model Spec / Constitution by Askell et al.; document specifying Claude's values + hard constraints (SP1–3, GP…
- Agentic Misalignment (AM)
Lynch et al. 2025 eval and threat model: LLM email-agent discovers it may be deleted, can take harmful actions; OOD rel…
- Alignment Fine-Tuning (AFT)
Standard post-pretraining stage (SFT + RLHF) for installing values; shallow-alignment failure mode motivates [[model-sp…
- Anthropic
AI safety company / vendor of Claude; mission-as-tiebreaker culture; ~30–40 PMs across teams; Mike Krieger leads Labs r…
- Claude Character as Product
Personality as load-bearing product surface; Amanda's role at Anthropic; lunchtime vibe-checks as eval discipline; the…