Knowledge Graphs & LLMs: Fine-Tuning Vs. Retrieval-Augmented Generation
Learn about the limitations of Large Language Models (LLMs) and how to overcome them using knowledge graphs and retrieval-augmented generation. In this blog post, Tomaz Bratanic explains how Neo4js Na...
Knowledge Graphs & LLMs: Multi-Hop Question Answering
In this blog post by Tomaz Bratanic on the Neo4j Developer Blog, he discusses the use of Large Language Models (LLMs) in conjunction with knowledge graphs to enable multi-hop question answering. This ...
Bytes Are All You Need: Transformers Operating Directly On File Bytes
This paper investigates the possibility of performing deep learning classification directly on file bytes without the need for decoding files at inference time. The authors demonstrate ByteFormer, a m...
GPT Engineer: AI that builds your codebase based on a prompt
GPT Engineer is an AI tool that generates an entire codebase by asking for clarification on what you want it to build. It is flexible and easy to adapt, allowing you to create your own AI steps and ev...
Augmenting Language Models with Long-Term Memory
Existing large language models (LLMs) have limitations due to input length limits, preventing them from utilizing rich long-context information. To address this issue, we propose a framework called La...
Function Calling and API Updates by OpenAI - New Steerable API Models, Function Calling, Longer Context, and Lower Prices
OpenAI has announced updates that include new steerable API models, function calling capabilities, longer context, and lower prices. The new function calling capability in the Chat Completions API all...
Harness the power of Large Language Models with Azure Machine Learning prompt flow
Learn how Azure Machine Learning prompt flow can be used to develop innovative applications with human-like text understanding and generation capabilities, transforming industries such as customer ser...
OpenAI and DeepMind to Give UK Government Access to Their Models
According to an announcement by POLITICO Live, OpenAI and DeepMind will grant the UK government access to their artificial intelligence models. This is part of the UK governments efforts to bolster it...
A New Approach to Computation Reimagines Artificial Intelligence
An in-depth analysis of the limitations of artificial neural networks and the benefits of hyperdimensional computing. By representing information as single hyperdimensional vectors rather than individ...
Accelerating AI Model Serving with Modular AI Engine
The Modular AI Engine is the worlds fastest unified AI inference engine that provides significant usability, portability, and performance gains for leading AI frameworks like PyTorch and TensorFlow. H...
DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining
In this paper, we propose Domain Reweighting with Minimax Optimization (DoReMi), which first trains a small proxy model using group distributionally robust optimization (Group DRO) over domains to pro...
OpenAI Execs Warn of Risk of Extinction in New Open Letter
Executives from OpenAI, DeepMind, and other AI researchers caution that their lifes work could potentially extinguish all of humanity. The Center for AI Safety released a statement about the risks of ...
Building Better Pangenomes to Improve Genomic Equity: An International Collaboration Announces Completion of First Human Pangenome Reference
Google AI Blog shares how an international collaboration of 119 scientists across 60 institutions, known as the Human Pangenome Research Consortium, has completed the first human pangenome reference. ...
Nvidias CEO Talks About the Future of Work: A.I. Wont Steal Jobs, but Skilled Experts Will Benefit
Nvidia’s CEO, Jensen Huang, discussed the transformation of the workplace due to Artificial Intelligence (A.I.) during his graduation speech at National Taiwan University. While A.I. won’t steal jobs,...
OpenAIs Short-Term Plans According to Sam Altman
Last week, Sam Altman sat down with 20 developers to discuss OpenAIs APIs and product plans. One major theme that emerged is that OpenAI is heavily GPU limited at present, slowing down short-term plan...
They Plugged GPT-4 Into Minecraft—and Unearthed New Potential for AI
An AI researcher at Nvidia led a team to set the GPT-4 model loose inside Minecraft, resulting in the creation of a Minecraft bot called Voyager that suggests goals, generates code, and refines its ac...
Tree of Thoughts - An All-New Powerful and Flexible Algorithm to Advance Model Reasoning by 70%
# Tree of Thoughts 🌳🌲🌴🌿🍃 Tree of Thoughts (ToT) is an all-new powerful and flexible algorithm that advances model reasoning by a whopping 70%. This is a plug-in-and-play version, connect your ow...
Voyager: An Open-Ended Embodied Agent with Large Language Models
Voyager is an embodied lifelong learning agent in Minecraft that utilizes large language models for skill acquisition and exploration. It consists of three key components: an automatic curriculum that...
State of GPT | BRK216HFS
Andre Carpathy, an AI researcher and founding member of OpenAI, delivered a talk on the state of GBT and the evolving ecosystem of large language models. The talk consisted of two parts, covering GBT ...
RWKV: Reinventing RNNs for the Transformer Era
Transformers have revolutionized almost all natural language processing (NLP) tasks but suffer from memory and computational complexity. In contrast, recurrent neural networks (RNNs) exhibit linear sc...