Person
Chris Olah
Chris Olah is a Canadian machine learning researcher and co-founder of Anthropic, known for work on mechanistic interpretability, the effort to understand the internal workings of neural networks.
AffiliationsOpenAIAnthropicGoogle Brain
Overview
Chris Olah is a Canadian machine learning researcher and a co-founder of Anthropic. He is known for work on neural network interpretability, especially mechanistic interpretability.[1][3]
Education and early career
He studied mathematics at the University of Toronto for a year without finishing a degree. He received a Thiel Fellowship in 2012.[1]
He worked at Google Brain from 2015 to 2018. There he did neural network visualisation work, including DeepDream.[1]
In 2017 he co-founded Distill, an interactive machine learning journal.[1]
Main contributions
From 2018 he led OpenAI's interpretability team. He collaborated on the Activation Atlases work in 2019.[1]
At Anthropic he leads work on mapping the internal “features” of large language models and linking that work to AI safety.[1]
He is a co-author of the Constitutional AI paper, published in December 2022.[2]
Career
He has worked at Google Brain, OpenAI and Anthropic, moving from interpretability research at OpenAI to leading similar work at Anthropic.[1][3]
Recognition and public remarks
He was named to the TIME100 AI list in 2024.[1]
In May 2026 he spoke at the presentation of Pope Leo XIV's encyclical Magnifica Humanitas. He warned of large-scale labour displacement by AI.[1]
Career timeline
4-
2015
-
Google Brain
Worked at 2015–2018
Google Brain was a deep-learning research team started inside Google's X in 2011. Its cat-recognition experiment, TensorFlow, sequence-to-sequence models and the Transformer made it central to modern AI; it merged into Google DeepMind in 2023.
-
Google Brain
Worked at 2015–2018
-
2018
-
OpenAI
Worked at 2018–2020
OpenAI is a San Francisco AI research and deployment company founded in 2015 as a nonprofit. It makes the GPT model family and ChatGPT and filed confidentially for an IPO in June 2026.
-
OpenAI
Worked at 2018–2020
-
2021
-
Anthropic
Founded、Worked at 2021–
Anthropic is an AI safety and research company founded in January 2021 by former OpenAI employees. It develops the Claude models and products, and its Responsible Scaling Policy sets out safety levels for its models.
-
Anthropic
Founded、Worked at 2021–
-
2022
-
Constitutional AI: Harmlessness from AI Feedback
Contributed to
Constitutional AI, a 2022 paper from Anthropic, proposes training a harmless AI assistant with AI-generated feedback guided by a written set of principles, instead of human labels of harmful outputs.
-
Constitutional AI: Harmlessness from AI Feedback
Contributed to
Founded1
20211
-
MilestoneAnthropic is founded
Anthropic, an AI company, was incorporated in January 2021 by former employees of OpenAI and set up as a public benefit corporation. Dario Amodei became its chief executive and Daniela Amodei its president.
Contributed to1
Notes and sources
- Chris Olahhttps://en.wikipedia.org/wiki/Chris_Olah
- Constitutional AI: Harmlessness from AI Feedbackhttps://arxiv.org/abs/2212.08073
- Anthropichttps://en.wikipedia.org/wiki/Anthropic
Cite this page: Chris Olah. TellWorld, https://www.tellworld.net/people/chris-olah. Updated 2026-11-08