Batch computing and the coming age of AI systems
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...
Task-driven Autonomous Agent Utilizing GPT-4, Pinecone, and LangChain for Diverse Applications - Yohei Nakajima
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 - Connect Your Data to Large Language Models
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...
Hype grows over “autonomous” AI agents that loop GPT-4 outputs
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...
DERA: Enhancing Large Language Model Completions with Dialog-Enabled Resolving Agents
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...
Reflexion: an autonomous agent with dynamic memory and self-reflection
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...
Max Tegmark: The Case for Halting AI Development | Lex Fridman Podcast #371

MIT physicist and AI researcher Max Tegmark, a key figure in the call for a six-month pause on giant AI experiments, returns to the Lex Friedman podcast. Tegmark discusses his belief that we are likel...
Amazon CodeWhisperer, Free for Individual Use, is Now Generally Available
Amazon CodeWhisperer, a real-time AI coding companion, is now generally available and includes a CodeWhisperer Individual tier that is free to use for all developers. The tool keeps developers product...
Teaching Large Language Models to Self-Debug
Large language models have achieved impressive performance on code generation, but generating correct code with a single attempt is challenging. To address this problem, the authors propose SELF-DEBUG...
Build your own ChatGPT in .NET with Semantic Kernel 🚀

The popularity of chat GPT, which has signed up 100 million users in just two months, has led to an increase in startups utilizing the underlying large language models (LLMs) that power the technology...
HuggingGPT - a Hugging Face Space by Microsoft
HuggingGPT is a space created by Microsoft under the Hugging Face umbrella, offering access to a range of models, datasets, and solutions. The space supports file sharing and has a vibrant community o...
Our Approach to AI Safety: Ensuring Safe and Beneficial Use of Powerful AI Systems
OpenAI is committed to building and deploying powerful AI systems safely and responsibly. We understand that AI tools come with real risks, which is why we conduct rigorous testing and engage with ext...
Welcome to LangChain - LangChain 0.0.133
LangChain is a powerful platform for developing and integrating natural language models, chat models, prompt templates, vector stores, and much more. Get started with our quickstart guide, and explore...
Neural Networks: Zero To Hero
This course by Andrej Karpathy is a step-by-step guide to building neural networks from scratch, starting with backpropagation and building up to modern deep neural networks like GPT. The focus is on ...
Andrej Karpathy: Tesla AI, Self-Driving, Optimus, Aliens, and AGI | Lex Fridman Podcast #333

Andre Capothy, the former director of AI at Tesla and OpenAI, defines neural networks as a mathematical abstraction of the brain. These networks consist of knobs that are modifiable and trainable, sim...
Attention is all you need by Vaswani et al.
The paper Attention is All You Need introduces the Transformer, a model based on attention which revolutionized the field of natural language processing. Unlike previous models, the Transformer relies...
Attention Is All You Need
The Transformer is a new simple network architecture based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Our experiments on two machine translation tasks show t...
# Bot Generator Bot
This is a Multi-Purpose Bot Prompt Generator designed to help users create customized prompts for various types of ChatGPT bots. With this tool, users can easily generate prompts for different types o...
Auto-GPT: An Autonomous GPT-4 Experiment
Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. This program, driven by GPT-4, autonomously develops and manages businesses to increase net...
GPT magic: A Jupyter/IPython command for generating code with GPT
# GPT magic A Jupyter/IPython magic command for generating code using GPT. Install with pip and provide your own OpenAI API key. Current default is gpt-3-turbo model with options to change to gpt-4. A...