In this paper, we propose Hyena, a subquadratic drop-in replacement for attention, constructed by interleaving implicitly parametrized long convolutions and data-controlled gating. Our proposed method...

In this TED talk, Greg Brockman, the CTO of OpenAI, explores the advanced capabilities of ChatGPT, an AI-powered chatbot that can generate human-like responses. He delves into how ChatGPT is revolutio...

Welcome to Jupyter AI, which brings generative AI to Jupyter. Jupyter AI provides a user-friendly and powerful way to explore generative AI models in notebooks and improve your productivity in Jupyter...

In this preprint, the authors propose MEMIT, a method for updating language models with many memories, scaling up to thousands of associations for large models like GPT-J (6B) and GPT-NeoX (20B), exce...

The co-founders of the Center for Humane Technology, Tristan Harris and ASA Raskin, discuss the potential dangers and irresponsible deployment of artificial intelligence (AI) in their presentation tit...

Earlier today, Google announced the formation of Google DeepMind, which combines the talents and efforts of the DeepMind and Brain teams from Google Research as a single, focused unit. The goal is to ...

# griptape [](https://pypi.python.org/pypi/griptape) [](https://griptape.readthedocs...

This article provides insights on the Semantic Kernel, a Software Development Kit that simplifies integration of language models into your own applications. It discusses the capabilities of the Semant...

Elon Musk, the founder of Tesla and SpaceX, has quietly started a new AI company called X.AI to challenge OpenAI. The company will focus on developing advanced AI technologies across various domains, ...

Transformer-based large language models are gaining a foothold in the field of machine learning research, with a plethora of applications in natural language processing, biology, chemistry, and comput...

Meet Marvin: a batteries-included library for building AI-powered software that introduces AI Functions and flexible bots. With AI functions, developers dont have to write complex code for tasks like ...

In this blog post, Scott Alexander reflects on Allen Ginsbergs famous poem Moloch, exploring the meaning and implications of this entity in modern society. He examines Molochs role in perpetuating hum...

MicroGPT is a simple and effective autonomous agent compatible with GPT-3.5-Turbo and GPT-4. The installation process involves cloning the repository, installing necessary Python packages, and configu...

This Python script demonstrates an AI-based task management system that utilizes OpenAI and Pinecone APIs to create, prioritize, and execute tasks. The script runs an infinite loop by pulling tasks fr...

Batch computing, the process of processing large amounts of data without human interaction, could be revolutionized by the use of foundation models. While current human-in-the-loop systems are already...

In this research, a task-driven autonomous agent is proposed that leverages OpenAIs GPT-4 language model, Pinecone vector search, and the LangChain framework to perform various tasks within different ...

Databerry provides a user-friendly solution to quickly setup a semantic search system over your personal data without any technical knowledge. Load data from various sources such as raw text, web page...

Since the launch of OpenAIs GPT-4 API last month to beta testers, developers have been experimenting with making agent-like implementations of the AI model that attempt to carry out multistep tasks wi...

In this work, we present dialog-enabled resolving agents (DERA) which is a paradigm that provides a simple, interpretable forum for models to communicate feedback and iteratively improve output with t...

Recent advancements in decision-making large language model (LLM) agents have demonstrated impressive performance across various benchmarks. However, these state-of-the-art approaches typically necess...