--- title: "Sam McCandlish — author profile and papers" description: "Sam McCandlish, Machine Intelligence Research Institute: 3 papers on Elamur Research (2020–2023), h-index 22 — affiliations, topics, co-authors and who…" canonical: "https://research.elamur.ai/free/en/authors/sam-mccandlish/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/sam-mccandlish/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Sam McCandlish # Sam McCandlish Sam McCandlish's papers here deal with [language models and pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), with a recurring interest in how model behaviour depends on scale. The typical method is empirical. Families of Transformer models are trained across wide ranges of size and data, and simple quantitative relationships are fitted to the results. A later strand moves from training loss to what models actually say, comparing their answers with human survey responses. The most cited work is [Scaling Laws for Neural Language Models](https://md.research.elamur.ai/free/en/papers/kaplan-2020-scaling-laws-neural-language-models/) (2020). It trained a long series of Transformers on the WebText2 corpus while varying model size, dataset size, training length, batch size and network shape. It found that test loss falls as a power law in parameters, data and compute, each considered on its own, as long as neither of the other two becomes the limiting factor. A follow-up, [Scaling Laws for Transfer](https://md.research.elamur.ai/free/en/papers/hernandez-2021-scaling-laws-transfer/) (2021), asks what pre-training is worth when the downstream task has little data. It expresses that benefit as an equivalent quantity of fine-tuning data and studies it across several orders of magnitude in model and dataset size. The newest paper, [Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://md.research.elamur.ai/free/en/papers/durmus-2023-towards-measuring-representation-subjective-global/) (2023), turns to the question of whose views a model's answers on contested social topics resemble. It introduces GlobalOpinionQA, a multiple-choice set built from the Pew Global Attitudes survey and the World Values Survey. The paper then compares a dialogue model's answer probabilities with country-level human answer distributions under several prompting conditions. The model studied was trained with RLHF and Constitutional AI. McCandlish's current affiliations are the Machine Intelligence Research Institute in Berkeley and the [University of Oxford](https://md.research.elamur.ai/free/en/universities/university-of-oxford/). Papers from 2021 and 2022 list [Anthropic](https://md.research.elamur.ai/free/en/companies/anthropic/). Frequent co-authors on the scaling work include [Jared Kaplan](https://md.research.elamur.ai/free/en/authors/jared-kaplan/), [Tom Henighan](https://md.research.elamur.ai/free/en/authors/tom-henighan/) and [Danny Hernandez](https://md.research.elamur.ai/free/en/authors/danny-hernandez/). Sam McCandlish has 3 papers in our library, in 2020–2023, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/); often with [Danny Hernandez](https://md.research.elamur.ai/free/en/authors/danny-hernandez/), [Jared Kaplan](https://md.research.elamur.ai/free/en/authors/jared-kaplan/), [Tom Henighan](https://md.research.elamur.ai/free/en/authors/tom-henighan/). 3 papers in our library · 2020–2023 [OpenAlex](https://openalex.org/A5054887773) · [**h-index 22**](https://openalex.org/authors/A5054887773) · [25 works](https://openalex.org/works?filter=author.id:A5054887773) · [7,979 citations](https://openalex.org/works?filter=author.id:A5054887773&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 3 works in our library](https://md.research.elamur.ai/free/en/authors/sam-mccandlish/#papers) · [🔗 4,762 citations in our library](https://md.research.elamur.ai/free/en/authors/sam-mccandlish/cited-by/) · [4 more in our library without a page yet](#also) · [⭐ Paper Star rank #1109](https://md.research.elamur.ai/free/en/paper-stars/page/12/#star-1109) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Sam+McCandlish) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Sam+McCandlish) · [dblp](https://dblp.org/search?q=Sam+McCandlish) · [ACL Anthology](https://aclanthology.org/search/?q=Sam+McCandlish) ## Affiliations [🤝**Machine Intelligence Research Institute** Berkeley · United States 2022–2023 · 2 papers*current*](https://ror.org/01h4ass90) · [🏢**Anthropic** San Francisco 2021–2022 · 3 papers](https://md.research.elamur.ai/free/en/companies/anthropic/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 2 more institutions on single bylines are not listed. ## Concepts, shelves and topics Of its works in our library: the number of works on each and its rating among them. 💡 Concepts 2[Scaling laws · 2 works](https://md.research.elamur.ai/free/en/concepts/scaling-laws/) · [Language model · 1 work](https://md.research.elamur.ai/free/en/concepts/language-model/) 📚 Shelves 3[AI & machine learning · 2 works](https://md.research.elamur.ai/free/en/shelves/ai/) · [Other · 1 work](https://md.research.elamur.ai/free/en/shelves/other/) · [Natural language processing · 1 work](https://md.research.elamur.ai/free/en/shelves/nlp/) 🧭 Topics 1[Language models & pretraining · 3 works](https://md.research.elamur.ai/free/en/topics/language-models/) ## Works by year ### 2020s [**2023** 1 paper](https://md.research.elamur.ai/free/en/papers/durmus-2023-towards-measuring-representation-subjective-global/) · [**2021** 1 paper](https://md.research.elamur.ai/free/en/papers/hernandez-2021-scaling-laws-transfer/) · [**2020** 1 paper](https://md.research.elamur.ai/free/en/papers/kaplan-2020-scaling-laws-neural-language-models/) ## Papers The most cited first (OpenAlex and our library). 1. **[Scaling Laws for Neural Language Models](https://md.research.elamur.ai/free/en/papers/kaplan-2020-scaling-laws-neural-language-models/)** *(2020 · 1,814 citations)* The authors from OpenAI study how the quality of a language model depends on its scale. They measure quality by the cross-entropy loss on test data. To this end, they trained a large series of Transformer models on the WebText2 corpus, ranging from thousands to roughly a billion parameters, excluding embeddings. In… 2. **[Towards Measuring the Representation of Subjective Global Opinions in Language Models](https://md.research.elamur.ai/free/en/papers/durmus-2023-towards-measuring-representation-subjective-global/)** *(2023 · 262 citations)* LLMs increasingly answer contested social questions, but it is unclear whose views those answers reflect. The Anthropic authors propose a way to measure this. They built GlobalOpinionQA, a multiple-choice dataset drawn from two cross-national surveys, Pew Global Attitudes and the World Values Survey. Each question… 3. **[Scaling Laws for Transfer](https://md.research.elamur.ai/free/en/papers/hernandez-2021-scaling-laws-transfer/)** *(2021 · 102 citations)* This paper asks how much language-model pre-training is worth when the target task has little data. It answers in units of data. The authors trained transformers across roughly four orders of magnitude in both non-embedding parameters and dataset size, using three curricula: ## Also in our library 4 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 12 of 18 co-authors with a page, the most papers together first. - [Danny Hernandez](https://md.research.elamur.ai/free/en/authors/danny-hernandez/) ×2 - [Jared Kaplan](https://md.research.elamur.ai/free/en/authors/jared-kaplan/) ×2 - [Tom Henighan](https://md.research.elamur.ai/free/en/authors/tom-henighan/) ×2 - [Alec Radford](https://md.research.elamur.ai/free/en/authors/alec-radford/) - [Amanda Askell](https://md.research.elamur.ai/free/en/authors/amanda-askell/) - [Anton Bakhtin](https://md.research.elamur.ai/free/en/authors/anton-bakhtin/) - [Carol Chen](https://md.research.elamur.ai/free/en/authors/carol-chen/) - [Dario Amodei](https://md.research.elamur.ai/free/en/authors/dario-amodei/) - [Esin Durmus](https://md.research.elamur.ai/free/en/authors/esin-durmus/) - [Karina Nguyen](https://md.research.elamur.ai/free/en/authors/karina-nguyen/) - [Liane Lovitt](https://md.research.elamur.ai/free/en/authors/liane-lovitt/) - [Nicholas Joseph](https://md.research.elamur.ai/free/en/authors/nicholas-joseph/) ## Cited by Papers of our library cite their works 4,762 times (of the 140,884 papers whose bibliographies we read); [331 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/sam-mccandlish/cited-by/). Updated 23 October 2026