LLM or custom model: how should you choose the right solution? https://towardsdatascience.com/do-you-really-need-a-foundation-model/

A curated collection of resources, papers, tools, and implementations that bridge the gap between Retrieval-Augmented Generation (RAG) and Reasoning in Large Language Models and Agents. This repository brings together traditionally separate research domains to enable more powerful Agentic AI systems. https://github.com/DavidZWZ/Awesome-RAG-Reasoning

PageSpace is an AI-native knowledge base that transforms your scattered documents, conversations, and project files into a single, intelligent, and perpetually searchable engine. https://github.com/2witstudios/pagespace.team

"From the invention of writing and the printing press, to television and social media, human history is punctuated by major innovations in communication technology, which fundamentally altered how ideas spread and reshaped our culture. Recent chatbots powered by generative artificial intelligence constitute a novel medium that encodes cultural patterns in their neural representations and disseminates them in conversations with hundreds of millions of people. Understanding whether these patterns transmit into human language, and ultimately shape human culture, is a fundamental question. While fully quantifying the causal impact of a chatbot like ChatGPT on human culture is very challenging, lexicographic shift in human spoken communication may offer an early indicator of such broad phenomenon. Here, we apply econometric causal inference techniques [10] to 740,249 hours of human discourse from 360,445 YouTube academic talks and 771,591 conversational podcast episodes across multiple disciplines. We detect a measurable and abrupt increase in the use of words preferentially generated by ChatGPT—such as delve, comprehend, boast, swift, and meticulous—after its release. These findings suggest a scenario where machines, originally trained on human data and subsequently exhibiting their own cultural traits, can, in turn, measurably reshape human culture. This marks the beginning of a closed cultural feedback loop in which cultural traits circulate bidirectionally between humans and machines. Our results motivate further research into the evolution of human-machine culture, and raise concerns over the erosion of linguistic and cultural diversity, and the risks of scalable manipulation." https://arxiv.org/pdf/2409.01754

"In the rapidly evolving landscape of large language models (LLMs), the spotlight has largely focused on the decoder-only architecture. While these models have shown impressive capabilities across a wide range of generation tasks, the classic encoder-decoder architecture, such as T5 (The Text-to-Text Transfer Transformer), remains a popular choice for many real-world applications. Encoder-decoder models often excel at summarization, translation, QA, and more due to their high inference efficiency, design flexibility, and richer encoder representation for understanding input. Nevertheless, the powerful encoder-decoder architecture has received little relative attention. Today, we revisit this architecture and introduce T5Gemma, a new collection of encoder-decoder LLMs developed by converting pretrained decoder-only models into the encoder-decoder architecture through a technique called adaptation. T5Gemma is based on the Gemma 2 framework, including adapted Gemma 2 2B and 9B models as well as a set of newly trained T5-sized models (Small, Base, Large and XL). We are excited to release pretrained and instruction-tuned T5Gemma models to the community to unlock new opportunities for research and development." https://developers.googleblog.com/en/t5gemma/