ChatGPT Programming Tutorials & Engineering Articles

One user turn can contain many model and tool iterations. Any cost inside the repeated region can be paid many times.

By Justin Uberti and Zahan Malkani, Members of Technical Staff

How to remain competitive in the AI era of software engineering

We've had decades to learn what it means to design software and hardware for humans. How do we build experiences where the primary user may now be an LLM?

Coding AI agents are becoming practical operators for long-running machine learning (ML) workflows. They can inspect repositories, set up runtimes…

Using population-level analysis to debug tricky crashes in our data infrastructure.

MRC’s support for multi-plane networks means we can connect over a hundred thousand GPUs with only two tiers of switches. This reduces the power required, the number of components that can fail, and the total cost of the network compared to conventional approaches.

By Yi Zhang and William McDonald, Members of Technical Staff

Marketing to agents is becoming as important as marketing to humans. We ran an experiment embedding tracked incentives on ramp.com pages addressed to AI agents. Here's what we learned.

The article introduces Markdown for Agents, a feature by Cloudflare that allows AI systems to request web content in Markdown format instead of HTML.

This article details the transformation of ClickHouse's internal data warehouse from a traditional BI-first approach to an AI-first model, significantly enhancing user accessibility to analytics.

Inside our new process architecture, which ​​gives you a faster, smarter way to use the web.

This article discusses the process of scaling LangGraph agents in production, specifically focusing on the deployment of an AI-Q research agent.

Building agents that learn directly from humans performing real work, unlocking scalable automation from just a single recording.

The article discusses the importance of LLM observability using ClickStack, OpenTelemetry, and MCP, highlighting how to instrument LibreChat for enhanced insights into AI-driven applications.

The article discusses the integration of NVIDIA BlueField-3 Data Processing Units (DPUs) with F5 BIG-IP Next for Kubernetes to enhance the deployment of agentic AI applications in cloud environment...

The article explores the analysis of Wimbledon tennis data using ClickHouse, detailing the unique scoring system of tennis and how to implement a function to compute points needed to win a game.

The article discusses the integration of ClickHouse with the Model Context Protocol (MCP), highlighting its benefits for connecting third-party services to large language models (LLMs).

The article discusses the NVIDIA AI Blueprint for an LLM router, which provides a cost-efficient framework for dynamically routing prompts to the most suitable large language models (LLMs).

The article discusses the transformation of traditional data centers into AI factories, driven by the increasing computational demands of AI workflows.

The article discusses how integrating large language models (LLMs) with knowledge graphs enhances the extraction of structured insights from unstructured data, addressing challenges faced by tradit...

The article discusses LinkedIn's commitment to connecting its members to economic opportunities through advanced AI technologies.

The article discusses the transformation of telecom networks to effectively manage and optimize AI workloads, particularly in the context of 5G technology and the rise of large language models (LLM...

The article discusses the use of a generative AI-enabled OpenUSD pipeline to produce cinematic content at scale, specifically for commercials.

The article discusses the development of a new reward model, Llama 3.

NVIDIA has introduced its first on-device small language model (SLM) aimed at enhancing game character interactions, showcased in the game Mecha BREAK.

The article discusses the launch of Continuum AI by Edgeless Systems, a generative AI framework that ensures data privacy through confidential computing and NVIDIA H100 GPUs.

The article introduces DoRA, a high-performing alternative to Low-Rank Adaptation (LoRA) for fine-tuning pretrained models.

NVIDIA's announcement at GDC 2024 highlights advancements in generative AI for digital human technologies and the introduction of AI-powered NVIDIA RTX lighting.

NVIDIA NIM is a set of optimized cloud-native microservices designed to facilitate the deployment of AI models at scale, addressing the complexities of AI model development and integration into ent...

This article details the process of building a chatbot named 'HackBot' that utilizes data from Hacker News and Stack Overflow, leveraging ClickHouse and LlamaIndex.

The article discusses how enterprises can build enterprise-grade AI applications using NVIDIA AI Software, focusing on the importance of optimized software for various stages of AI development.

The article discusses how NVIDIA is enhancing the performance of large language model (LLM) applications on Windows PCs equipped with NVIDIA RTX systems.

The article reviews the most popular NVIDIA Technical Blog posts of 2023, highlighting advancements in generative AI, large language models (LLMs), high-performance computing (HPC), and robotics.

The article introduces the NVIDIA GH200 NVL32, a groundbreaking superchip designed for large language models (LLMs), recommender systems, and graph neural networks (GNNs).