The American Economy has become the envy of the world 🚀🚀🚀🇺🇸🇺🇸🇺🇸

When I took office, we faced the worst economic crisis since the Great Depression. Today, we have the greatest economy in the world.

John Horton Makes sense! We push with full force in this direction: x.com/mbodhisattwa/s…

Fantastic opportunity to do cutting edge work on LLM agents - in an open, nonprofit environment!

3/ 🔍 What is OpenScholar? It's a retrieval-augmented LM with 1️⃣ a datastore of 45M+ open-access papers 2️⃣ a specialized retriever and reranker to search the datastore 3️⃣ an 8B Llama fine-tuned LM trained on high-quality synthetic data 4️⃣ a self-feedback generation pipeline

Very cool scientific QA system - try it!

Great review of OpenScholar venturebeat.com/ai/openscholar… Try it at: openscholar.allen.ai

Curious people's reaction to this... How should one design for effective human-AI communication?

Nice work on a method and UI for human-ai teaming! arxiv.org/abs/2412.10999 Task is the process of performing scientific research, but technique is general. With Kevin Feng Joseph Chee Chang Amy Zhang and many more

Exciting chance to work with a phenomenal team, producing open AI tech for the common good! Apply now!

More great work by FutureHouse!

Joint work with Amanpreet Singh Aakanksha Naik Sergey Feldman Pao Siangliulue Kyle Lo Doug Downey Daniel Weld and more. Please check it out and give us feedback : )

This is still experimental, but ... really cool! Try it!

Try our new scientific question answering system!

Check it out! allenai.org/blog/ai2-schol…

Introducing olmOCR, our open-source tool to extract clean plain text from PDFs! Built for scale, olmOCR handles many document types with high throughput. Run it on your own GPU for free—at over 3000 token/s, equivalent to $190 per million pages, or 1/32 the cost of GPT-4o!

Use the power of LLMs to find academic papers for your hardest queries!

Need someone (or something!) to amplify the speed of your ML/NLP experimentation rate?

The trouble with finding a specific papers you read but forgetten is there's a diff between 1)what the paper says 2) what other people cite it for 3) what YOU want to cite it for! Trying ai2 paper finder makes it clear ha

AI2 Paper Finder and AI2 ScholarQA are the best tools for finding related works. I'm surprised they aren't more popular Ai2