Nous Research's RLHF LLM 🤖 // Microsoft's AI-powered Office 💻 // Fine-tuning GPT-3.5 for "Connections" 🕹️

Nous Research has released their new flagship LLM, Nous-Hermes 2, which is the first model trained with RLHF and the first model to beat Mixtral Instruct in popular benchmarks. Microsoft's Copilot Pro brings AI-powered Office features to consumers for $20 a month, including the ability to generate entire PowerPoint slide decks from a chatbot-like prompt and rephrase paragraphs in Word. A blog post explores fine-tuning gpt-3.5-turbo to learn how to play "Connections", demonstrating the potential of fine-tuning language models for specific tasks. Three research papers are discussed, including the effects of pretraining data curation on language models, a new benchmark for evaluating multimodal large language models on image-based wordplay puzzles, and the major shortcomings identified in these models. Contact:  [email protected] Timestamps: 00:34 Introduction 01:37 Nous Research Releases new flagship LLM 02:50 Microsoft’s new Copilot Pro brings AI-powered Office features to the rest of us 05:03 Fine-tuning gpt-3.5-turbo to learn to play "Connections" 06:08 Fake sponsor 08:02 AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters 09:36 AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters 11:19 REBUS: A Robust Evaluation Benchmark of Understanding Symbols 13:11 Outro