Yoshua Bengio says that if you want to win the next Turing Award you should work on something other than deep learning. Reading this book is a good place to start: amazon.com/Rebooting-AI-B…

One thing we loved about 2023 was the volume of new research around RAG from the entire community ❤️. This survey by Gao et al. is the most comprehensive survey of this research we’ve seen yet - it covers 100+ papers, blog posts, and projects across every step of the RAG

This is a neat qualitative example by Micky Multani highlighting why you should always include reranking in your advanced RAG pipeline 💡 ✅ For simple queries, naive RAG is fine. ⚠️ For advanced queries though, you need a reranker to return precise relevant context to answer

Do you want your recommendation system to also learn what the users DISLIKE? jeevg.substack.com/p/handling-neg… papers quoted: arxiv.org/pdf/2308.12256 lnkd.in/eFtGmJfd cc: Yueqi Wang

Setting up a team to fine-tune Gemma on Nepali language for this Kaggle competition due in a month -- lnkd.in/ekQ4mNgi Any Nepali engineers/interns who want to contribute or learn, please dm!

This paper is wild - a Stanford team shows the simplest way to make an open LLM into a reasoning model. They used just 1,000 carefully curated reasoning examples & a trick where if the model tries to stop thinking, they append "Wait" to force it to continue. Near o1 at math.

eKantipur: Nepalis fly kites for a cause in New York goo.gl/fb/CUF8d

News of the event held at Cornell to support #OccupyBaluwatar published in Kantipur Daily. epaper.ekantipur.com/showtext.aspx?…

@For_bohemia Hey!!! found you on Twitter!! whats up??

Chek out, "What We're Reading in Financial Regulatory Reform", August 29 bipartisanpolicy.org/blog/financial… via Bipartisan Policy Center

@SocrataSupport Hey read.socrata doesn't end while trying to access an API in R. It would be great if I could get some help.