Skip to main content ->
Ai2

Ai2 blog

November 2024 - OLMo 2: The best fully open language model to date

Our next generation of fully-open base and instruct models sit at the Pareto frontier of performance and training efficiency. Check out our paper to learn more, or keep reading for a summary.

Chris Bretherton / December 2024 - The Ai2 Climate Emulator

The Ai2 Climate Emulator: Fast, accurate AI-based atmospheric simulation for historical and future climates.

November 2024 - Tülu 3: The next era in open post-training

A technical deep-dive into Tülu 3, with the model "recipe", data, and more.

Peter Hase / January 2024 - The unreasonable effectiveness of easy training data

Language models can perform well on hard, domain-specific questions when trained only on easy questions.

Patrick Beukema / December 2023 - AI for Earth, 2023 in review

Environmental AI advancements in 2023 that joined the fight to protect the environment.

Ali Farhadi / December 2023 - The CREATE AI Act is essential to AI innovation in the United States

The CREATE AI Act is not just about technology; it's about democratizing opportunity.

Brian Henn / December 2023 - Stable and fast: ACE, the Ai2 Climate Emulator

We present ACE, a 200M-parameter, autoregressive machine learning emulator of an existing global atmospheric model.

Patrick Beukema / December 2023 - Protecting marine life with AI

In environmental conservation, AI represents a paradigm shift that can be used as a powerful force for good.

Hamish Ivison / December 2023 - Camels in a changing climate: Enhancing LM adaptation with Tulu 2

How far we can further push the limits of open-source models? This is the question researchers tackle with Tulu 2.

December 2023 - Featured Ai2er: Jenna James

How Jenna James began to pursue UX Design, which led to her work on fighting wildfires via technology at Ai2.

Hyunwoo Kim / November 2023 - Does GPT-4 have theory of mind capabilities?

The FANToM benchmark analyzes theory of mind capabilities of 13 state-of-the-art LLMs based on essential criteria.

Hyunwoo Kim / November 2023 - Are you thirsty for social chitchat data?

We introduce SODA, the first million-scale high-quality social chitchat dataset.