Large Language Models Programming Tutorials & Engineering Articles

Training an LLM is the easy part. The hard part is designing experiments and evaluations that you can trust enough to know whether the new…

AI performance comes down to three dimensions: Deployments must balance all three: High accuracy is wasted if responses are slow, and raw throughput means…

The Google Tunix Hackathon on Kaggle challenged developers to transform small, non-reasoning base models into general reasoning engines using Kaggle TPUs and a limited compute budget. The winning teams achieved this by implementing multi-stage post-training pipelines that combined Supervised Fine-Tuning (SFT) with advanced alignment techniques like GRPO and SimPO. Ultimately, the competition democratized AI development by proving that highly capable, structured reasoning models can be successfully trained by the community using accessible, open-source resources.

Google has released version 1.0.0 of the Agent Development Kit (ADK) for Java, introducing powerful new features like Google Maps grounding, built-in URL fetching, and a standardized Agent2Agent protocol for cross-framework collaboration. The update enhances agent control through a new "App" and "Plugin" architecture, which allows for global logging, automated context window management via event compaction, and "Human-in-the-Loop" workflows for action confirmations. Additionally, the release provides robust session and memory services using Google Cloud integrations like Firestore and Vertex AI to manage long-term state and large data artifacts.

Google announces the public preview of the Developer Knowledge API and its associated Model Context Protocol (MCP) server, providing a canonical, machine-readable gateway to Google's official devel...

This tutorial demonstrates how to fine-tune FunctionGemma, a small language model for translating natural language into API calls, using Google's Tunix library on TPUs.

The article discusses the NVIDIA Nemotron 3, a family of open models designed for agentic AI systems, emphasizing its efficiency and accuracy through innovative architectures and techniques.

The article discusses Pinterest's approach to enhancing its observability tools by integrating AI and the Model Context Protocol (MCP).

Slack's Security Engineering team describes how they built an AI agent-based system to automate and streamline security investigations.

The NVIDIA Blackwell architecture has achieved the fastest training times across all MLPerf Training v5. 1 benchmarks, showcasing significant advancements in AI training performance.

The article discusses Meta's evolution in infrastructure over 21 years, highlighting the significant changes brought about by AI.

The article discusses the integration of the Apigee Operator for Kubernetes with the GKE Inference Gateway to enhance API management for AI and Large Language Models (LLMs).

The article discusses a new approach to bot management that leverages behavioral anomaly detection tailored for individual customers.

The article discusses the integration of Google’s Agent Development Kit (ADK) for Java with the LangChain4j LLM framework, enabling developers to utilize a variety of Large Language Models (LLMs) f...

The article discusses how to enhance the efficiency of Large Language Models (LLMs) during inference by utilizing CPU-GPU memory sharing through NVIDIA's NVLink C2C technology.

This article discusses the integration of Google's EmbeddingGemma model with Google Cloud's Dataflow to create a scalable embedding pipeline for AI applications.

The article discusses Cloudflare's introduction of unsafe content moderation integrated into its Firewall for AI, aimed at protecting Large Language Models (LLMs) from malicious prompts that could ...

The article discusses the transformative impact of AI on various industries and introduces Cloudflare's AI Week 2025, focusing on enhancing security and control over AI technologies.

This article provides a comprehensive guide on how to train a GPT-2 model using JAX on TPU, highlighting the ease of leveraging Google TPUs for free.

Cloudflare has partnered with OpenAI to integrate their new open-weight models into Cloudflare Workers AI, allowing developers to leverage these models for enhanced AI capabilities.

The article discusses Shopify's Global Catalogue, which utilizes multimodal Large Language Models (LLMs) to standardize and enrich product data across its platform.

The article introduces GenAI Processors, an open-source Python library from Google DeepMind aimed at simplifying the development of sophisticated AI applications using Large Language Models (LLMs).

The article explores the changing dynamics of web crawling and referral traffic due to the rise of AI and Large Language Models (LLMs).

This article discusses how to build an agentic application using ClickHouse MCP Server and CopilotKit, focusing on creating a customizable analytics dashboard for the UK real estate market.

The article discusses JUDE, LinkedIn's platform for generating high-quality embeddings for job recommendations using fine-tuned Large Language Models (LLMs).

This article serves as a comprehensive guide for benchmarking Large Language Models (LLMs) using NVIDIA's GenAI-Perf tool alongside NVIDIA NIM.

The article discusses the implementation of a Large Language Model (LLM)-based relevance system for Pinterest Search, detailing its technical design, model architecture, and the results from both o...

The article discusses the evolution of LinkedIn's Nuage control plane, highlighting its transition from a self-service platform to a comprehensive control plane solution for managing data infrastru...

The article discusses Netflix's development of a Foundation Model for Personalized Recommendation, which aims to centralize member preference learning and enhance the efficiency of their recommenda...

This article provides a comprehensive guide on Vision Language Models (VLMs) and their evolution from single-image understanding to advanced video comprehension.

The article discusses the Marco framework, a configurable graph-based task-solving and multi-AI agent system designed to streamline chip design processes.

NVIDIA has released a new Generative AI Teaching Kit aimed at enhancing education in generative AI technologies.

The article discusses Gemma, a family of lightweight generative AI models, and introduces the concept of Agentic AI, which allows AI to make proactive decisions and utilize external tools.

The article discusses the Vertex AI RAG Engine, a tool designed to help developers build grounded generative AI applications by addressing challenges like hallucinations and outdated knowledge.

The article discusses the upgraded Claude 3. 5 Sonnet model, which achieved a score of 49% on the SWE-bench Verified benchmark, surpassing the previous state-of-the-art model's score of 45%.

The article discusses the implementation of data-efficient knowledge distillation using NVIDIA NeMo-Aligner during supervised fine-tuning (SFT).

The article introduces the Prompt Engineering Toolkit developed by Uber, which aims to streamline the process of creating and managing prompts for Large Language Models (LLMs).

The article discusses the ethical implications and operational realities of implementing AI Decision Support Systems (AI-DSS) in military contexts.

The article discusses how Slack is utilizing AI-powered tools to enhance developer productivity and streamline processes.

The article discusses the challenges and solutions involved in scaling the AI Gateway on the Cloudflare Developer Platform, specifically focusing on extending log storage capabilities from 30 minut...

This article discusses the implementation of Ray Batch Inference at Pinterest, highlighting its advantages over previous solutions like Apache Spark and Torch Dataloader.

The article discusses Cloudflare's new tools that empower site owners to audit and control how AI models access their content.

NVIDIA showcased its AI security expertise at the Black Hat USA and DEF CON conferences, focusing on the evolving landscape of AI in cybersecurity.

The article discusses the deployment of diverse AI applications using Multi-LoRA support on NVIDIA RTX AI PCs and workstations.