Jason Wei
I was previously a research scientist at Google Brain, where I popularized some key ideas in large language models: chain-of-thought prompting, instruction tuning, and emergent phenomena. Chain-of-thought prompting was presented by Sundar Pichai at the Google I/O press event in 2022. Twitter / CV / Google scholar / Email
Papers 2025 Apr A simple yet challenging benchmark for browsing agents. (blog) 2024 Oct Measuring short-form factuality in large language models. (blog) 2022 Oct Scaling instruction-finetuned language models. (blog) 2022 Jun Emergent abilities of large language models. (blog) 2022 Jan Chain-of-thought prompting elicits reasoning in language models. (blog) 2021 Sep Finetuned language models are zero-shot learners. (blog) 2019 Jan Easy data augmentation techniques for text classification tasks. Talks & Media 2025 Oct Talk, Stanford AI Club (youtube). 2025 Mar Keynote, Columbia…
saved by
related reading
- Yi Tayyitay.net
- [2201.11903] Chain of Thought Prompting Elicits Reasoning in Large Language Modelsarxiv.org
- [2203.14465] STaR: Bootstrapping Reasoning With Reasoningarxiv.org
- As Rocks May Think | Eric Jangevjang.com
- Tracing the thoughts of a large language model \ Anthropicanthropic.com
- [2201.11903] Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelsarxiv.org
- GitHub - brexhq/prompt-engineering: Tips and tricks for working with Large Language Models like OpenAI's GPT-4.github.com
- Explore | alphaXivalphaxiv.org
- The Unintelligibility is Ours: Notes on Chain of Thought1a3orn.com
- Language Models Perform Reasoning via Chain of Thoughtai.googleblog.com
- Thoughts — Jason Weijasonwei.net
- How AI Is Learning to Think in Secretnickandresen.substack.com