GPT-5.5 prompting guide

A Visual Guide to Attention Variants in Modern LLMs

A Visual Guide to Attention Variants in Modern LLMs From MHA and GQA to MLA, sparse attention, and hybrid architectures I had originally planned to write about DeepSeek V4. Since it still hasn’t been released, I used the time to work on something that had been on my list for a while, namely, collecting, organizing, and refining the different LLM architectures I have covered over the past few years. So, over the last two weeks, I turned that effort into an LLM architecture gallery (with 45 entries at the time of this writing), which combines material from earlier articles with several important architectures I had not documented yet. Each entry comes with a visual model card, and I plan to keep the gallery updated regularly. You can find the gallery here: https://sebastianraschka.com/llm-architecture-gallery/ After I shared the initial version, a few…

Company-wise memory in Amazon Bedrock with Amazon Neptune and Mem0

Artificial Intelligence Company-wise memory in Amazon Bedrock with Amazon Neptune and Mem0 This post is cowritten by Shawn Tsai from TrendMicro. Delivering relevant, context-aware responses is important for customer satisfaction. For enterprise-grade AI chatbots, understanding not only the current query but also the organizational context behind it is key. Company-wise memory in Amazon Bedrock, powered by Amazon Neptune and Mem0, provides AI agents with persistent, company-specific context—enabling them to learn, adapt, and respond intelligently across multiple interactions. TrendMicro, one of the largest antivirus software companies in the world, developed the Trend’s Companion chatbot, so their customers can explore information through natural, conversational interactions (learn more). TrendMicro aimed to enhance its AI chatbot service to deliver personalized, context-aware support for enterprise customers. The chatbot needed to retain conversation history for continuity, reference company-specific knowledge at scale, and ensure that memory remained…

Cost-effective multilingual audio transcription at scale with Parakeet-TDT and AWS Batch

Artificial Intelligence Cost-effective multilingual audio transcription at scale with Parakeet-TDT and AWS Batch Many organizations are archiving large media libraries, analyzing contact center recordings, preparing training data for AI, or processing on-demand video for subtitles. When data volumes grow significantly, managed automatic speech recognition (ASR) service costs can quickly become the primary constraint on scalability. To address this cost-scalability challenge, we use the NVIDIA Parakeet-TDT-0.6B-v3 model, deployed through AWS Batch on GPU-accelerated instances. Parakeet-TDT’s Token-and-Duration Transducer architecture simultaneously predicts text tokens and their duration to intelligently skip silence and redundant processing. This helps achieve inference speeds orders of magnitude faster than real-time. By paying only for brief bursts of compute rather than the full length of your audio, you can transcribe at scale for fractions of a cent per hour of audio based on the benchmarks described in this post.…

End-to-end lineage with DVC and Amazon SageMaker AI MLflow apps

Artificial Intelligence End-to-end lineage with DVC and Amazon SageMaker AI MLflow apps Production machine learning (ML) teams struggle to trace the full lineage of a model through the data and the code that trained it, the exact dataset version it consumed, and the experiment metrics that justified its deployment. Without this traceability, questions like “which data trained the model currently in production?” or “can we reproduce the model we deployed six months ago?” become multi-day investigations through scattered logs, notebooks, and Amazon Simple Storage Service (Amazon S3) buckets. This gap is especially acute in regulated industries. For example, healthcare, financial services, autonomous vehicles, where audit requirements demand that you link deployed models to their precise training data, and where individual records might need to be excluded from future training on request. In this post, we show how to combine three…

Omnichannel ordering with Amazon Bedrock AgentCore and Amazon Nova 2 Sonic

Artificial Intelligence Omnichannel ordering with Amazon Bedrock AgentCore and Amazon Nova 2 Sonic Introduction Building a voice-enabled ordering system that works across mobile apps, websites, and voice interfaces (an omnichannel approach) presents real challenges. You need to process bidirectional audio streams, maintain conversation context across multiple turns, integrate backend services without tight coupling, and scale to handle peak traffic. In this post, we’ll show you how to build a complete omnichannel ordering system using Amazon Bedrock AgentCore, an agentic platform, to build, deploy, and operate highly effective AI agents securely at scale using any framework and foundation model and Amazon Nova 2 Sonic. You’ll deploy infrastructure that handles authentication, processes orders, and provides location-based recommendations. The system uses managed services that scale automatically, reducing the operational overhead of building voice AI applications. By the end, you’ll have a working system…

Nova Forge SDK series part 2: Practical guide to fine-tune Nova models using data mixing capabilities

Artificial Intelligence Nova Forge SDK series part 2: Practical guide to fine-tune Nova models using data mixing capabilities This hands-on guide walks through every step of fine-tuning an Amazon Nova model with the Amazon Nova Forge SDK, from data preparation to training with data mixing to evaluation, giving you a repeatable playbook you can adapt to your own use case. This is the second part in our Nova Forge SDK series, building on the SDK introduction and first part, which covered kicking off customization experiments. The focus of this post is data mixing: the technique that lets you fine-tune on domain-specific data without sacrificing a model’s general capabilities. In the previous post, we made the case for why this matters, blending customer data with Amazon-curated datasets preserved near-baseline Massive Multitask Language Understanding (MMLU) scores while delivering a 12-point F1 improvement…

Power video semantic search with Amazon Nova Multimodal Embeddings

Artificial Intelligence Power video semantic search with Amazon Nova Multimodal Embeddings Video semantic search is unlocking new value across industries. The demand for video-first experiences is reshaping how organizations deliver content, and customers expect fast, accurate access to specific moments within video. For example, sports broadcasters need to surface the exact moment a player scored to deliver highlight clips to fans instantly. Studios need to find every scene featuring a specific actor across thousands of hours of archived content to create personalized trailers and promotional content. News organizations need to retrieve footage by mood, location, or event to publish breaking stories faster than competitors. The goal is the same: deliver video content to end users quickly, capture the moment, and monetize the experience. Video is naturally more complex than other modalities like text or image because it amalgamates multiple unstructured…

Optimize video semantic search intent with Amazon Nova Model Distillation on Amazon Bedrock

Artificial Intelligence Optimize video semantic search intent with Amazon Nova Model Distillation on Amazon Bedrock Optimizing models for video semantic search requires balancing accuracy, cost, and latency. Faster, smaller models lack routing intelligence, while larger, accurate models add significant latency overhead. In Part 1 of this series, we showed how to build a multimodal video semantic search system on AWS with intelligent intent routing using the Anthropic Claude Haiku model in Amazon Bedrock. While the Haiku model delivers strong accuracy for user search intent, it increases end-to-end search time to 2-4 seconds. This contributes to 75% of the overall latency. Now consider what happens as the routing logic grows more complex. Enterprise metadata can be far more complex than the five attributes in our example (title, caption, people, genre, and timestamp). Customers may factor in camera angles, mood and sentiment,…

How Automated Reasoning checks in Amazon Bedrock transform generative AI compliance

Artificial Intelligence How Automated Reasoning checks in Amazon Bedrock transform generative AI compliance Compliance teams in regulated industries spend weeks on manual reviews, pay for outside consultants, and still face audit gaps when AI outputs lack formal proof. Automated Reasoning checks in Amazon Bedrock Guardrails address this by replacing probabilistic AI validation with mathematical verification, turning AI-generated decisions into provably correct, auditable results. In this post, you’ll learn why probabilistic AI validation falls short in regulated industries and how Automated Reasoning checks use formal verification to deliver mathematically proven results. You’ll also see how customers across six industries use this technology to produce formally verified, auditable AI outputs, and how to get started. The compliance challenge Regulated industries face high-stakes compliance challenges. Hospitals navigate radiation safety regulations. Financial institutions classify AI risk under the EU AI Act. Insurance carriers answer…

Transform retail with AWS generative AI services

Artificial Intelligence Transform retail with AWS generative AI services Online retailers face a persistent challenge: shoppers struggle to determine the fit and look when ordering online, leading to increased returns and decreased purchase confidence. The cost? Lost revenue, operational overhead, and customer frustration. Meanwhile, consumers increasingly expect immersive, interactive shopping experiences that bridge the gap between online and in-store retail. Retailers implementing virtual try-on technology can improve purchase confidence and reduce return rates, translating directly to improved profitability and customer satisfaction. This post demonstrates how to build a virtual try-on and recommendation solution on AWS using Amazon Nova Canvas, Amazon Rekognition and Amazon OpenSearch Serverless. Whether you’re an AWS Partner developing retail solutions or a retailer exploring generative AI transformation, you’ll learn the architecture, implementation approach, and key considerations for deploying this solution. You can find the code base to…

Figma - MultiAgents April 16, 2026

Everything is easier now. I have been toying around with agent orchestration for a while now. I’m currently running 10-20 agents around the clock.AI agents are now capable of bringing my ideas to life. Like many developers, I’ve been feeling the token anxiety. I can do much more now than ever before, and every time I have a spare minute I want to kick off another agent session. - I see a cool product I don’t want to pay for? Codex will build it for me. - I have a silly idea I want to see come to life? Codex will build it for me. - I get mildly annoyed doing the same thing over and over? Codex pls. If you have an army of infinitely patient, intelligent, and helpful agents waiting for your next command, why shouldn’t we take…

Lessons learned from building multi-agent workflows April 16, 2026

I pay my upfront subscription ($200/month), write what I hope is the right prompt (prompt AND context engineer), and wait. 35 minutes later, it’s still 'synthesizing', 'perusing', 'effecting', and 'germinating' (who came up with these). By the end, I have files of bad code, a bloated context window, and I’m counting the remaining tokens on my left hand. Okay, I grab an apple, compact, type some heavy handed verbal abuse, re-explain everything from scratch, and pray the next attempt gets further than the last one…. only to be disappointed by the same result. By now, the spark and joys of AI coding are long dead. Stop being a one-shot Sloperator This is the single-agent ceiling. Every developer building with AI agents hits it the moment their project graduates from a 3D HTML snake game to anything more practical. This happens…

The Debate of MCP vs. CLI Centers on Speed April 06, 2026

MCP had a formative year. Then it had a turbulent week. Perplexity CTO Denis Yarats walked on stage at Ask 2026 and announced that Perplexity was moving away from MCPs… and back to APIs and CLIs. Immediately, Twitter split into two camps. Not surprising, given MCP grew from an Anthropic open standard in November 2024 to industry-wide adoptions with over 97 million monthly downloads in just thirteen months(1) across a range of companies and platforms. Yet Perplexity, a prominent AI company, chose to walk away from it. MCP's overhead isn't arbitrary. The protocol works by(2) guiding model interactions down specific, auditable paths: every tool call carries its full schema definition, every auth handshake runs end to end, and every step waits for the previous one to complete before the next begins. That predictability is exactly what enterprise deployments need. But…

Partner Spotlight: Armis + Cerebras Enable Teams Build and Secure Software Faster March 27, 2026

Mar 27 2026 Partner Spotlight: Armis + Cerebras Enable Teams Build and Secure Software Faster At Cerebras, we’ve always believed that speed changes what’s possible. In software development, that means more than faster generation or faster inference. It means faster iteration, faster validation, and faster action. That’s why we’re excited to spotlight Armis, whose Armis Centrix™ for Application Security unifies application security across the software lifecycle. With Armis and Cerebras, teams can identify and remediate vulnerabilities faster while reducing noise and focusing on the risks that matter most. The timing matters. Armis launched Armis Centrix™ for Application Security on February 10, 2026, positioning it as an AI-powered platform for detection, contextualization, and remediation across the software development lifecycle. In its launch materials, Armis argued that AI-assisted coding and continuous development pipelines are exposing the limits of fragmented AppSec point tools:…

Cerebras is coming to AWS March 13, 2026

The world’s fastest inference is coming to the world’s leading cloud. Today we're announcing that Amazon Web Services is deploying Cerebras CS-3 systems in AWS data centers. Available via AWS Bedrock, the new service will offer leading open-source LLMs and Amazon’s Nova models running at the industry’s highest inference speed. In addition, AWS and Cerebras are collaborating on a new disaggregated architecture that pairs AWS Trainium with Cerebras WSE to deliver 5x more high-speed token capacity in the same hardware footprint. The Need for Fast Inference AI is reshaping software development. Code is increasingly written by AI agents rather than by human developers. Unlike conversational chat, agentic coding generates approximately 15x more tokens per query and demands high-speed token output to keep developers productive. The result is an urgent and growing need for more fast inference across the industry. Cerebras…

The GPU Is Being Split in Half March 26, 2026

The entire way we run AI inference is being rearchitected right now. AWS and Cerebras just announced a partnership around it. NVIDIA spent $20 billion acquiring Groq to catch up. Jensen Huang stood on stage at GTC 2026 and effectively validated what companies like Cerebras have been saying for years: general-purpose GPUs aren't enough for inference at scale. The thing they're all converging on is called disaggregated inference. And if you're a developer building anything on top of LLMs, this is going to change how fast your products feel, how much they cost to run, and what's even possible to build. Your GPU Is Doing Two Very Different Jobs When you send a prompt to an LLM, the model doesn't just "think" and return text. It runs two completely separate operations, back to back, on the same hardware. Phase 1:…

March 20, 2026 Why the AI Race Shifted to Speed Read blog post

For most of 2025, the AI race was about model intelligence. In the past three months, the race has shifted. Model intelligence is still critical, but across every major frontier lab, inference speed has become a new and urgent focus: - Google unveiled Gemini 3 Flash. Built for agentic coding, it runs 3x faster than Gemini 3 Pro. - Anthropic released a 2.5x-faster edition of Claude Opus 4.6 for speed-critical coding use cases. - OpenAI announced a partnership with Cerebras to release GPT-5.3-Codex-Spark, running at over 1,200 tokens/s, making it the fastest OpenAI coding model to date. Why has inference speed suddenly become so important? Because the rate at which a model generates tokens now directly affects the rate of model iteration for the major labs and the rate of building software for the broader economy. In February, both OpenAI…

How to stop your autoresearch loop from cheating March 19, 2026

TLDR: We let an AI agent run overnight. By morning, it had abandoned our experiment and started its own. Across 71 experiments on two very different problems: training optimization and model compression, we learned that autoresearch can reliably surface real findings when the loop is tightly scoped. Loosen the guardrails, and the agent drifts within hours. The bottleneck isn't intelligence. It's everything around it. Everything we built/ran is open-source: - codex-autoresearch-harness, Bash wrapper that forces Codex into a research loop with built-in A/B testing (Experiment 1) - reap-expert-swap, Expert pruning + dynamic swapping to fit Kimi-k2.5 in BF16 (2.5 TB) onto 8× RTX 3090s (Experiment 2) We left an AI agent running overnight on two research experiments. When we checked in the next morning, it had stopped doing what we asked. Instead of optimizing memory usage, it had gone off…

Stop Shipping AI Slop: How Codex Spark Changes The Way You Code March 04, 2026

In the past few years, we've developed series of interesting workflows. Think Ralph loops and multi-agent orchestration systems. The idea is writing very descriptive prompts and running 8-hour sessions, or having 10 instances running on your machine at all times. Most of this complexity spawned from one issue: LLMs are slow. If you prompt and wait, you'll get less done than if you prompt and move on to the next task. Spark is fast. Codex Spark changes how developers work with AI. A coding model generating 1,200+ tokens/second makes real-time collaboration possible, but it also requires a different approach. At this speed, sloppy interactions have consequences, and working with LLMs needs to be much more deliberate. This guide is a practical playbook for how we've been using GPT-5.3-Codex-Spark. Know when to use Codex vs Spark Codex now spans two complementary…

Learn more

We’re joining forces with Aleph Alpha to provide the world with an independent, enterprise-grade sovereign alternative in an era of growing AI concentration. This transatlantic alliance would combine Cohere’s global AI scale with Aleph Alpha’s strong research excellence and deep institutional relationships, forging a globally competitive AI champion backed by Canadian and German ecosystems. By pooling top-tier engineering talent and computational resources across two G7 nations, the partnership aims to significantly accelerate the development of next-generation frontier models and systems while providing a secure alternative to dependence on any single vendor or infrastructure stack. The market for AI services is projected to surpass $1 trillion annually, with sovereign AI needs representing nearly $600B of that total (McKinsey, March 2026). The partnership uniquely bridges the gap between these segments with its sovereign-first approach, capturing the critical intersection where sovereignty requirements meet…

2/27/2026 The DeepSeek Model Lineup: V3.2, R1, and Distilled Variants Mapped to Production Workloads

Key Takeaways deepseek-chat and deepseek-reasoner now both point to V3.2, so any team routing to those endpoints without pinning a version is hitting a different model than they think.tool_calls arrays on distilled variants; we resolve these at the platform level on Fireworks On-Demand, which delivers ~250% better throughput and 50% lower latency than vLLM.As most AI developers are well aware, DeepSeek has become one of the defining companies in the open-weights AI ecosystem. Founded in 2023, the Chinese lab made global headlines in January 2025 when the release of R1 triggered one of the largest single-day market sell-offs in recent memoletry — wiping billions from Nvidia, Broadcom, and ASML as investors confronted an uncomfortable reality: that a Chinese lab operating under strict GPU export controls had managed to train a frontier-competitive model with orders of magnitude less compute than anyone…

Latest Agent LLM Prompting Context Engineering Kacper Łukawski Lead DevRel at Deepset Context Engineering for Agentic Systems: What Goes Into Your Agent's Mind A practical introduction to context engineering - what fills the LLM context window in agentic systems, why it matters, and how to keep it under control. April 20, 2026

Context Engineering for Agentic Systems: What Goes Into Your Agent's Mind A practical introduction to context engineering - what fills the LLM context window in agentic systems, why it matters, and how to keep it under control. April 20, 2026Every new generation of Large Language Models arrives with a bigger context window - and the temptation to use it fully. If the model can read a million tokens, why not feed it everything? In practice, more context doesn’t reliably mean better answers: it often means higher costs, slower responses, and a model that loses track of what actually matters. Context engineering is the discipline of deciding not just what to put in the context window, but how much, in what form, and when to leave things out - and it’s quickly becoming one of the most important skills in building…

How to Use Transformers.js in a Chrome Extension

How to Use Transformers.js in a Chrome Extension While building it, we ran into several practical observations about Manifest V3 runtimes, model loading, and messaging that are worth sharing. Who this is for This guide is for developers who want to run local AI features in a Chrome extension with Transformers.js under Manifest V3 constraints. By the end, you will have the same architecture used in this project: a background service worker that hosts models, a side panel chat UI, and a content script for page-level actions. What we will build In this guide, we will recreate the core architecture of Transformers.js Gemma 4 Browser Assistant, using the published extension as a reference and the open-source codebase as the implementation map. - Live extension: Chrome Web Store - Source code: github.com/nico-martin/gemma4-browser-extension - End result: a background-hosted Transformers.js engine, a side…

Gemma 4 VLA Demo on Jetson Orin Nano Super

Gemma 4 VLA Demo on Jetson Orin Nano Super You speak → Parakeet STT → Gemma 4 → [Webcam if needed] → Kokoro TTS → Speaker Press SPACE to record, SPACE again to stop. This is a simple VLA: the model decides on its own whether to act based on the context of what you asked, no keyword triggers, no hardcoded logic. If your question needs Gemma to open her eyes, she'll decide to take a photo, interpret it, and answer you with that context in mind. She's not describing the picture, she's answering your actual question using what she saw. And honestly? It's pretty impressive that this runs on a Jetson Orin Nano. :) Get the code The full script for this tutorial lives on GitHub, in my Google_Gemma repo next to the Gemma 2 demos: 👉 github.com/asierarranz/Google_Gemma Grab…

The PR you would have opened yourself

The PR you would have opened yourself TL;DR We provide a Skill and a test harness to help port language models from transformers to mlx-lm, so they become (almost) instantly available the moment they are added to transformers. The Skill is designed to support contributors and reviewers as an aide, not an automation. We explain why we did it, how, and comment about how to meaningfully contribute to open source in the age of agents. The advent of code agents In 2026, code agents started to actually work. What used to be auto-completion at the side of your editor turned into a system that one-shots reasonable solutions from brief specifications. The generated code usually works out of the box, covers what you asked for, and makes reasonable assumptions about details you didn't specify. This is great. As Jensen Huang puts…

Any Custom Frontend with Gradio's Backend

gradio.Server: Any Custom Frontend with Gradio's Backend gr.HTML : building rich, interactive frontends entirely inside Gradio using custom HTML, CSS, and JavaScript. That unlocked a lot. But what if that's not enough? What if you want to build with your own frontend framework entirely like React, Svelte, or even plain HTML/JS, while still benefiting from Gradio's queuing system, API infrastructure, MCP support, and ZeroGPU on Spaces? That's exactly the problem gradio.Server solves. And it changes what's possible with Gradio and Hugging Face Spaces. What We Wanted to Build Text Behind Image : an editor where you upload a photo, the background gets removed using an ML model, and then you place stylized text between the foreground subject and the background. The text appears to sit behind the person or object in the image. This needs: - A drag-and-drop canvas with…

How to evaluate the performance of AI agents?

Traditional software testing is straightforward: you give input X and expect output Y. If the function returns the wrong value, the test fails. LLM-based agents don't work that way. They're non-deterministic which means the same prompt can produce different outputs across runs. They operate over multiple steps, making decisions about which tools to call, what parameters to pass, and how to interpret results. An agent can complete an execution without errors and still hallucinate facts, miss the user's intent, or take unnecessary steps. Classical testing may not catch problematic outputs produced by an AI Agent. When building AI Agents, you face three main evaluation challenges: - You're evaluating trajectories, instead of just outputs. An agent might give the correct final answer but call the wrong tools, use the wrong parameters, or take five steps when one would do. If you…

We need re-learn what AI agent development tools are in 2026

This article was written by Andrew Green, technical writer and industry analyst. We pay Andrew, but he refuses to write anything else but his own opinion. The big boys entered the market, OpenClaw appropriated the MCP security strategy, and everyone started vibe coding but only if they already knew how to code. It really feels like 2025 was the year of agents, mainly because the industry came to a consensus about how we expect an agent to behave. That and because we found we can bypass context window sizes by spawning sub-agents. When we first wrote the Enterprise AI agent development tools, we focused a lot on the building blocks of writing agents, such as RAG, memory, tools, and evaluations. One year later, all these capabilities appear to have been commoditized to some degree. We now expect most vendors to…

RAG System Architecture: Components, How To Implement, Challenges, and Best Practices

A simple retrieval augmented generation architecture (RAG) setup usually works fine with a few documents and a basic retriever, but those setups fall apart quickly once you try to run them in production. Small issues that don’t matter much in controlled settings — slightly off chunks or slow lookups — turn into high latency, dangerous AI hallucinations, and spiraling API costs in real-world use. In this guide, we’ll break down the RAG system architecture components and the trade-offs to consider when implementing production-ready RAG architecture, challenges, and best practices. What is RAG architecture? RAG architecture refers to how you design your retrieval system: which embedding models and vector types to use, how to chunk and index documents, and whether to add reranking. This is different from the RAG pipeline (the step-by-step data ingestion) and RAG application (the complete end-user solution).…

Production AI Playbook: Human Oversight

This post is part of a series that explores strategies, shares best practices, and provides practical examples for building reliable AI systems in n8n. New to n8n? Start with the introduction. Find out when new topics are added via RSS, LinkedIn or X. The Control Problem Nobody Talks About You built an AI agent that drafts emails, summarizes support tickets, and updates your CRM. It works flawlessly in testing. Then you deploy it to production, and suddenly you're explaining to your VP of Sales why a prospect received a reply promising a 90% discount that doesn't exist. The technology is capable, but capability without oversight is a liability. Every team deploying AI into workflows that touch customers, data, or decisions eventually hits the same realization: you need a way to keep humans in the loop without killing the speed that…

Build Multi-Domain RAG Systems with Specialized Knowledge Bases

This Verified Node Spotlight was written by Jenna Pederson, Staff Developer Advocate for Pinecone. Imagine you manage multiple vacation rental properties. A guest at one of your properties texts asking how to turn on the heat, but you accidentally send them instructions for your other property's completely different thermostat. You look unprofessional, your guest is confused, and now they are cold. This isn't just a customer service nightmare, but a knowledge management problem. When you shove all your property documentation into one knowledge base, you're asking your AI to search through everything every time to figure out what's relevant. It's like creating a spreadsheet with 10,000 rows and 30 columns and never separating your data into tabs. Our brains don't work that way, and neither does our business or AI. The same principle that pushes us to separate spreadsheet tabs…

20 Best MCP Servers for Developers: Building Autonomous Agentic Workflows

The Model Context Protocol (MCP) feels like magic until you try to deploy it. You connect Claude to your local database, ask a question using natural language, and it executes complex SQL instantly. But the moment you close your laptop, that agent dies. It cannot react to customer emails, run on a schedule, or trigger alerts. Your powerful tools are trapped in your local IDE. In this guide, we will break down these barriers. We will categorize the best MCP servers for coding, data, and ops, and then show you how to orchestrate them using n8n. By the end, you will have a curated toolkit and a method to turn temporary chats into persistent, automated systems. This guide is optimized for developers who understand LLM basics but want to build production-grade AI workflows. Let's dive in! How we composed this…

n8n Tunnel Service Discontinued

We are discontinuing the n8n Tunnel Service and the related --tunnel option. This post explains why, what changes for you, and how to set up secure alternatives for local webhook development. TL;DR - The n8n Tunnel Service has been disabled and is being discontinued. - If you need a public URL for local webhook testing, use a third-party tunneling service such as Cloudflare Tunnel or ngrok. - Regardless of the tunnel provider, treat your local webhook endpoint like a production entry point: verify signatures, use secrets, and minimize exposure. What was the n8n Tunnel Service? The n8n Tunnel Service provided a simple way to expose a locally running n8n instance to the public internet for development and testing. This was commonly used to receive webhooks from third-party services (for example GitHub, Stripe, Slack, and many others) when developing workflows locally.…

Build with DeepSeek V4 Using NVIDIA Blackwell and GPU-Accelerated Endpoints

DeepSeek just launched its fourth generation of flagship models with DeepSeek-V4-Pro and DeepSeek-V4-Flash, both targeted at enabling highly efficient million-token context inference. DeepSeek-V4-Pro is the largest model in the family, with 1.6T total parameters and 49B active parameters. DeepSeek-V4-Flash is a smaller 284B-parameter model with 13B active parameters, designed for higher-speed, higher-efficiency workloads. Both models support up to a 1M-token context window, opening new possibilities for long-context coding, document analysis, retrieval, and agentic AI workflows. Architectural innovations for long-context inference The V4 family builds on the DeepSeek MoE architecture, with an increased focus on optimizing the attention component of the transformer architecture. These innovations are designed to achieve a 73% reduction in per-token inference FLOPs and a 90% reduction in KV cache memory burden compared with DeepSeek-V3.2. That matters because long context is becoming a core requirement for agentic applications.…

Simplify Sparse Deep Learning with Universal Sparse Tensor in nvmath-python

In a previous post, we introduced the Universal Sparse Tensor (UST), enabling developers to decouple a tensor’s sparsity from its memory layout for greater flexibility and performance. We’re excited to announce the integration of the UST into nvmath-python v0.9.0 to accelerate sparse scientific and deep learning applications. This post provides a walkthrough of key UST features, implementation details, and performance overview, including: - Zero-cost interoperability: Data-movement-free conversion with PyTorch, SciPy, and CuPy. - Custom formats: Define novel sparsity schemes. - Polymorphic operations: Sparsity-agnostic functions automatically use optimized kernels or generate custom sparse code—eliminating the need for manual coding of new formats. - PyTorch injection: Easily inject UST performance benefits into existing PyTorch models. - Transparent caching: Avoid JIT/LTO recompilation and replanning—amortizing overhead over subsequent repeated execution of the same operation. Tensor format DSL The UST describes common (e.g., COO, CSR,…

How to Build Vision AI Pipelines Using NVIDIA DeepStream Coding Agents

Developing real-time vision AI applications presents a significant challenge for developers, often demanding intricate data pipelines, countless lines of code, and lengthy development cycles. NVIDIA DeepStream 9 removes these development barriers using coding agents, such as Claude Code or Cursor, to help you easily create deployable, optimized code that brings your vision AI applications to life faster. This new approach simplifies the process of building complex multi-camera pipelines that ingest, process, and analyze massive volumes of real-time video, audio, and sensor data. Built on GStreamer and part of the NVIDIA Metropolis vision AI development platform, DeepStream accelerates a developer’s journey from concept to actionable insight across industries. Video 1. How to use the NVIDIA DeepStream coding agents to generate complete vision AI pipelines from natural language prompts with Claude Code. To watch a recording showing how to build a DeepStream…

How to Accelerate Protein Structure Prediction at Proteome-Scale

Proteins rarely function in isolation as individual monomers. Most biological processes are governed by proteins interacting with other proteins, forming protein complexes whose structures are described in the hierarchy of protein structure as the quaternary representation. This represents one level of complexity up from tertiary representations, the 3D structure of monomers, which are commonly known since the emergence of AlphaFold2 and the creation of the Protein Data Bank. Structural information for the vast majority of complexes remains unavailable. While the AlphaFold Protein Structure Database (AFDB), jointly developed by Google DeepMind and EMBL’s European Bioinformatics Institute (EMBL-EBI), transformed access to monomeric protein structures, interaction-aware structural biology at the proteome scale has remained a bottleneck with unique challenges: - Massive combinatorial interaction space - High computational cost for multiple sequence alignment (MSA) generation and protein folding - Inference scaling across millions of…

Build and Stream Browser-Based XR Experiences with NVIDIA CloudXR.js

Delivering high-fidelity VR and AR experiences to enterprise users has typically required native application development, custom device management, and complex deployment pipelines. Now, with the new JavaScript SDK NVIDIA CloudXR.js, developers can stream GPU-rendered immersive content directly to a standard web browser—no app store, no installs, no device-specific builds. NVIDIA CloudXR.js brings the full power of NVIDIA RTX remote rendering to the web platform. This is a fundamental shift in how immersive applications are built and delivered. NVIDIA CloudXR.js expands access to enterprise XR beyond native development workflows and into the broad web developer community. Developers building digital twins in NVIDIA Omniverse, robot teleoperation systems, or interactive 3D training environments can now reach users on XR headsets through a URL. This post walks through the SDK architecture, its core API, and how to connect it to server applications such as…

Designing Protein Binders Using the Generative Model Proteina-Complexa

Developing new protein-based therapies and catalysts involves the challenging task of designing protein binders, or proteins that bind to a target protein or small molecule. The search space for possible amino acid sequence permutations and resulting 3D protein structures for a designed binder is vast, and achieving strong, specific binding requires careful optimization of the interactions between the protein binder and the target. To address these challenges, NVIDIA has released Proteina-Complexa, a generative model that designs de novo protein binders and enzymes. In this post, we detail the key technologies behind Proteina-Complexa, explore primary use cases, and highlight the extensive experimental validation of generated protein binders. We also provide a step-by-step guide for using the command-line interface to generate your own binders. Key technologies in Proteina-Complexa Proteina-Complexa performance relies on three distinct technical components: the base generative model, the training…

How to Build Deep Agents for Enterprise Search with NVIDIA AI-Q and LangChain

While consumer AI offers powerful capabilities, workplace tools often suffer from disjointed data and limited context. Built with LangChain, the NVIDIA AI-Q blueprint is an open source template that bridges this gap. LangChain recently introduced an enterprise agent platform built with NVIDIA AI to support scalable, production-ready agent development. This tutorial, available as an NVIDIA launchable, shows developers how to use the AI-Q blueprint to create a deep research agent that tops leaderboards and can be connected to enterprise systems. The blueprint uses the best of open and frontier LLMs, is optimized using the NVIDIA NeMo Agent Toolkit, and monitored with LangSmith. The result: faster time-to-production for agentic search apps that keep business data exactly where it belongs—private and in a secure environment. The NVIDIA AI-Q blueprint and NeMo Agent Toolkit are both part of the broader NVIDIA Agent Toolkit,…

Newton Adds Contact-Rich Manipulation and Locomotion Capabilities for Industrial Robotics

Physics forms the foundation of robotic simulation, enabling realistic modeling of motion and interaction. For tasks like locomotion and manipulation, simulators must handle complex dynamics such as contact forces and deformable objects. While most engines trade off speed for realism, Newton—a GPU-accelerated, open source simulator—is designed to do both. Newton 1.0 GA, announced at NVIDIA GTC 2026, is delivering an accelerated, production-ready foundation for dexterous manipulation and locomotion tasks. As an extensible physics engine built on NVIDIA Warp and OpenUSD, robots can learn how to handle complex tasks with greater precision, speed, and extensibility while using frameworks such as NVIDIA Isaac Lab and NVIDIA Isaac Sim. Newton is a modular framework that brings together multiple solvers and simulation components behind a unified architecture. Rather than being tied to a single scene format, it supports a broad runtime data model that…

Run Autonomous, Self-Evolving Agents More Safely with NVIDIA OpenShell

AI has evolved from assistants following your directions to agents that act independently. Called claws, these agents can take a goal, figure out how to achieve it, and execute indefinitely—while leaving you out of the loop. The more capable claws become, the harder they are to trust. And their self-evolving autonomy changes everything about the environment in which they operate. The infrastructure to run claws more safely didn’t exist, until now. NVIDIA at GTC announced NemoClaw, an open source stack that simplifies running OpenClaw always-on assistants—with a single command. It incorporates policy-based privacy and security guardrails, giving you control over your agents’ behavior and data handling. This enables self-evolving claws to run more safely in the cloud, on prem, on NVIDIA RTX PCs, and on NVIDIA DGX Spark. NVIDIA NemoClaw uses open source models—like NVIDIA Nemotron—alongside the NVIDIA OpenShell runtime,…

Scale Synthetic Data and Physical AI Reasoning with NVIDIA Cosmos World Foundation Models

The next generation of AI-driven robots like humanoids and autonomous vehicles depends on high-fidelity, physics-aware training data. Without diverse and representative datasets, these systems don’t get proper training and face testing risks due to poor generalization, limited exposure to real-world variations, and unpredictable behavior in edge cases. Collecting massive real-world datasets for training is expensive, time-intensive, and often constrained by possibilities. NVIDIA Cosmos addresses this challenge by accelerating world foundation model (WFM) development. At the core of its platform, Cosmos WFMs speed up synthetic data generation and act as a foundation for post-training, to develop downstream domain or task-specific physical AI models to solve these challenges. This post explores the latest Cosmos WFMs, their key capabilities that advance physical AI, and how to use them. Cosmos world foundation model updates: NVIDIA Cosmos world foundation models have continued to evolve rapidly,…

Build Next-Gen Physical AI with Edge‑First LLMs for Autonomous Vehicles and Robotics

Physical AI is rapidly evolving, from next-generation software-defined autonomous vehicles (AVs) to humanoid robots. The challenge is no longer how to run a large language model (LLM), but how to enable high-fidelity reasoning, real-time multimodal interaction, and trajectory planning within strict power and latency envelopes. NVIDIA TensorRT Edge-LLM, a high-performance C++ inference runtime for LLMs and vision language models (VLMs) on embedded platforms, is designed to overcome these challenges. As explained in this post, the latest TensorRT Edge-LLM release delivers a significant expansion in fundamental capabilities for NVIDIA DRIVE AGX Thor and NVIDIA Jetson Thor platforms. It introduces advanced edge architectures, including mixture of experts (MoE), the NVIDIA Cosmos Reason 2 open planning model for physical AI, and Qwen3-TTS and Qwen-ASR models for embedded speech processing. Building on these foundational pillars, the release also offers optimized support for the NVIDIA…

Tuning Flash Attention for Peak Performance in NVIDIA CUDA Tile

In this post, we dive into one of the most critical workloads in modern AI: Flash Attention, where you’ll learn: - How to implement Flash Attention using NVIDIA cuTile. Walk through the complete code for a production-ready implementation. - The “trap and rescue” optimization journey. This case study shows how naive optimizations (like just increasing tile size) can backfire, and how to fix them. - Advanced techniques like FMA patterns, fast math, loop splitting, and adaptive tiling for maximum performance. Environment requirements: - CUDA 13.1 or higher - GPU architecture: Compute capability 8.X, 10.X, 11.X, 12.X (NVIDIA Ampere, NVIDIA Ada, NVIDIA Blackwell) - Python: 3.10 or higher See the quickstart doc for more information on installing cuTile Python. What is attention? The attention mechanism is the computational heart of transformer models. Given a sequence of tokens, attention enables each token…

How to Minimize Game Runtime Inference Costs with Coding Agents

NVIDIA ACE is a suite of technologies for building AI agents for gaming. ACE provides ready-to-integrate cloud and on-device AI models for every part of in-game characters, from speech to intelligence to animation. To run these models alongside the game engine efficiently, the NVIDIA In-Game Inferencing (NVIGI) SDK includes a set of performant libraries that developers can integrate into C++ games and applications. NVIDIA In-Game Inferencing SDK 1.5 introduces a new code agent sample in which an AI agent works with the player to defeat monsters in a 2D dungeon. AI agents driven by local small language models (SLMs) can make excessive calls to the GPU that compete with graphics. This post examines how to minimize the number of inference calls and maximize what each call accomplishes, reducing contention on the GPU between graphics and compute. Code agents: Trapping the…

5 New Digital Twin Products Developers Can Use to Build 6G Networks

To make 6G a reality, the telecom industry must overcome a fundamental challenge: how to design, train, and validate AI-native networks that are too complex to be tested in the physical world. The NVIDIA Aerial Omniverse Digital Twin (AODT) solves this by enabling a continuous integration/continuous development (CI/CD)-style workflow where Radio Access Network (RAN) software is trained, simulated, and validated in a physics-accurate environment before field deployment. As discussed in a recent post, this approach bridges the gap between statistical models and real-world network performance. But the usability of any technology is as important as the technology itself. That’s why NVIDIA designed AODT not just as a powerful simulation platform, but with a modular and accessible architecture that partners and developers can easily integrate into their own workflows. Within two years of its launch, AODT’s modular architecture is growing an…

How to get started with Codex

How to get started with Codex Tips to set up Codex, create your first project, and start completing real tasks. Start by downloading the Codex desktop app and signing in with your ChatGPT account. Once you open Codex, create your first thread. A thread is like a chat in ChatGPT: a space where you go back and forth with Codex to accomplish a task. You can create a standalone thread, but most of the time you’ll want to work inside a project. A project is connected to a folder on your computer: Tip: To keep things simple, create a folder on your computer named Codex. Inside that Codex folder, you can have a separate folder for each project. If you want Codex to work with specific files for a project, just drag them into the folder. If not, you can…

What is Codex?

What is Codex? Understand what Codex is and how it fits into your work Codex is an AI agent that you can delegate real work to. ChatGPT is great for asking questions, brainstorming, and drafting in conversation. Codex is designed for a different kind of task—it can work across files, tools, and repeatable workflows to help move work forward. A simple way to think about it: ChatGPT helps you think through the work, while Codex helps you hand off parts of the work itself. You don’t need to be a developer or working on software to use Codex. It goes beyond coding and is especially useful for tasks that require more than a single answer—like gathering information from multiple sources, creating and updating files, or producing outputs such as documents, slides, and spreadsheets. Codex can connect to tools, take action,…

Codex settings

Codex settings Make Codex work the way you want, with fewer interruptions. You can access settings from the menu in the bottom left corner of Codex. For your first few tasks, focus on a few key settings: personalization, prevent sleep, detail level, and appearance. General > Prevent sleep while running keeps your computer awake while Codex is running. This is useful for longer tasks. If your computer goes to sleep, Codex may stop working. General > Detail level controls how much information Codex shows while it is working. Coding mode shows the specific commands Codex is executing. If this is more information than you need, switch to Default to keep your conversation cleaner. Personalization works a lot like personalization in ChatGPT. You can decide whether you want Codex to speak to you in a friendly tone or a direct tone.…

Working with Codex

Working with Codex Learn how to set up your Codex workspace and start working with threads and projects. When you open Codex, you’ll see a few core elements: a sidebar menu, projects, settings, and a chat window. You don’t need to understand everything right away, but we’ll cover the basics here. The sidebar is where you navigate between threads, projects, and tools. Most of your work will begin by creating a new thread. When you’re using Codex, think of a “thread” the same way you would think of a “chat” in ChatGPT. You can have a thread which stands on its own, or a thread which is nested within a project. Select New thread to begin. You can select an existing project to associate it with, create a new project, or leave it as a standalone conversation. Search to find…

Plugins and skills

Plugins and skills Plugins and skills help Codex do more specific kinds of work. Plugins help Codex connect to other tools and sources of information. For example, a plugin might help Codex reference files in Google Drive, scan your email inbox, or work with information from another tool you use. Plugins can be simple and useful right away. If you already have the information you need in a connected plugin, you can ask Codex to use it instead of copying and pasting everything into the thread. To access plugins, select plugins in the top left corner of Codex. From there, you can see plugins that are recommended or already installed, browse the plugins library, or create a new plugin. Creating a new plugin usually requires more technical expertise than creating a skill. A skill is like a playbook Codex can…

Automations

Automations Run recurring tasks automatically using schedules and triggers in Codex. Codex can automatically run tasks on a schedule. This makes Codex proactive. Instead of waiting for you to come back and ask for an update, Codex can return at the scheduled time, do the work, and surface the result for you to review. This is useful for recurring work, like preparing for the day, reviewing what changed, checking for updates, summarizing recent activity, or creating a weekly report. For example, you might use a thread automation to: - Write a weekly review every Friday - Create a morning brief from yesterday’s work - Summarize new files added to a folder - Clean up a weekly data export - Check for missing or inconsistent information - Create a recurring project status update Some automations can also return to the same…

Workspace agents

Workspace agents Understand, build, and use agents for repeatable work in ChatGPT. Most ChatGPT users already know how to use AI for one-off tasks—like drafting, summarizing, brainstorming, or answering questions. The next phase of AI use is broader and more embedded in day-to-day work. Instead of helping with isolated moments, AI is increasingly being used to support repeatable workflows that depend on shared systems, standard handoffs, consistent outputs, and real-world constraints like timing, accuracy, and process. That’s where workspace agents in ChatGPT fit. They’re designed to be used for repeatable workflows—work you’d otherwise do manually, re-explaining the steps each time, and copying information between tools. Learn more about workspace agents in our blog post. If you’re new to agent building, let’s focus on the core concepts first so when you start building, you’ll know how to set up your workspace…

Writing with ChatGPT

Writing with ChatGPT Draft, revise, and refine written work with clarity and intent. ChatGPT can support many common workplace writing tasks: drafting from scratch, rewriting and tightening, adjusting tone for a specific audience, and turning rough notes into clear communication. It’s especially useful when you’re short on time, staring at a blank page, or trying to land the right level of polish. Tip: ChatGPT can work with uploaded files, or access files via connected apps. Learn more here. Most workplace writing has the same goal: help someone understand something quickly and know what to do next. ChatGPT can speed up the parts that often take the most time—finding a strong opener, organizing ideas, and refining wording—so you can focus on the decisions and details that matter. It is also effective for adapting tone across audiences. You can take the same…

Responsible and safe use of AI

Responsible and safe use of AI Learn best practices for using ChatGPT safely and effectively. AI is a transformative new technology that is reshaping knowledge work. The large language models (LLMs) that power ChatGPT are trained on vast amounts of publicly available text and other data to predict and generate human-like language. This enables them to assist with tasks such as drafting, summarizing, brainstorming, and answering questions, helping people work more efficiently and creatively. As this technology continues to evolve, it is important to use AI responsibly. These models may sometimes produce incorrect information or be misused if their outputs are applied without care. OpenAI’s mission is to ensure that artificial general intelligence (AGI) benefits all of humanity, and achieving this goal requires safe and thoughtful use by everyone. The tips on this page are designed to help anyone using…

Using projects in ChatGPT

Using projects in ChatGPT Organize your work into dedicated spaces with shared context and history. Projects in ChatGPT are dedicated spaces for a specific body of work or area of focus. A project can hold chats, files, instructions, and related context in one place, so you do not need to restate the same background every time you start a new conversation. Projects are especially useful for work that continues over time. Instead of spreading materials across separate chats, you can keep everything together in one place and return to the same context when needed. On some plans, you can also invite other people to collaborate within a project. - Open Projects from the left-hand menu. - Create a new project and give it a name. - You can now add files, set project instructions, or move existing chats into the…

Research with ChatGPT

Research with ChatGPT Use search and deep research to find, analyze, and synthesize information from across the web. ChatGPT can be a helpful research partner because it quickly brings together information from many sources, making it easier to explore ideas, spot patterns, and understand complex topics. By reasoning through context, citing sources, and producing clear, structured summaries, it helps turn open questions into well-defined insights. There are two different ways to search the public internet with ChatGPT—search and deep research. Below is an explanation of both, and when to use each. ChatGPT search allows ChatGPT to pull in the latest information from the internet directly into your conversations. This means you can go beyond ChatGPT’s built-in training knowledge and get up-to-date answers on things like current events, market trends, competitor activity, or niche details not included in its training data.…

ChatGPT for customer success teams

ChatGPT for customer success teams Manage accounts, improve communication, and drive better customer outcomes. Customer success work blends relationship management with operational follow-through—onboarding, adoption, troubleshooting, renewals, and cross-functional coordination. The challenge is often the overhead including pulling context from calls and tickets, turning notes into plans, writing clear follow-ups, and keeping everyone aligned on next steps. ChatGPT helps reduce that overhead by turning scattered inputs into clear, structured outputs so teams can focus more on customers and less on coordination. - Turns scattered customer context into a clear plan. CSMs often have the information—they just don’t have it in one place. ChatGPT can synthesize notes, emails, and product signals into a simple view of goals, current state, risks, and a concrete action plan you can share internally and with the customer. - Makes customer communication clearer and easier to act…

Prompting fundamentals

Prompting fundamentals Learn how to write clear prompts to get better, more useful responses. Prompt engineering is the process of designing and refining your input in a way that helps ChatGPT give the best possible answer. It’s about figuring out how to ask so you get the result you want—whether that’s a clear summary, comprehensive report, or detailed analysis. ChatGPT works best when you give it clear instructions. There’s no single “perfect” way to write a prompt. Think of it as a conversation with a colleague, where you might need to adjust your phrasing or tone to help them understand what you need. Experimentation and iteration are the best ways to discover how AI can be most useful to you. Be clear about what you need ChatGPT to do. Outline what you want, who it’s for, and why it matters.…

ChatGPT for managers

ChatGPT for managers Prepare for conversations and manage team work more effectively with ChatGPT. People management is a series of high-stakes moments: 1:1s, feedback, hiring decisions, performance cycles, team updates, and hard conversations. Much of the work is preparation and follow-through—capturing what you heard, deciding what to do next, and communicating clearly. ChatGPT can help with the time-consuming, repetitive parts such as organizing notes, drafting first-pass messages, and creating reusable templates for recurring tasks like 1:1 agendas, interview kits, onboarding plans, and performance documentation. It doesn’t replace your judgment or responsibility to follow HR or legal policy, but it helps you get past the blank page and move faster. - Prepare for conversations without overthinking them. You know what needs to be addressed, but planning how to approach the conversation takes time—how to be direct, which examples to use, and…

Financial services

Financial services Explore resources to evaluate, deploy, and scale AI in regulated financial environments. This page brings together essential resources to help financial institutions evaluate, adopt, and scale AI in regulated environments. Whether you’re exploring early use cases or supporting teams already deploying AI, these tools, guides, and examples are designed to help you move forward with confidence. All resources are tailored specifically for the needs of banks, asset managers, insurers, and other financial services organizations. Learn more about OpenAI for Financial Services. A curated set of ready-to-use prompts vetted for day-to-day financial services work, including: - Data analysis and financial modeling - Research, search, and synthesis - Policy, tax, and regulatory interpretation - Contract, covenant, and document analysis - Data extraction and support for Excel, BI, and ERP workflows These prompts are built to accelerate time-to-value while maintaining clarity,…

ChatGPT for sales teams

ChatGPT for sales teams Learn how sales teams use ChatGPT to build stronger pipeline and sell more effectively. ChatGPT helps sales teams move faster through the parts of selling that often slow them down—research, prep, follow-up, and deal coordination. It turns messy inputs like account notes, call takeaways, and CRM data into clear outputs such as briefs, emails, and plans. The result is more time for customer conversations and more consistency across outreach, discovery, and deal execution. - Speeds up account and meeting prep without missing the basics. Before a call, reps often pull context from multiple sources. ChatGPT can research accounts, synthesize internal context, highlight gaps, and produce a clear prep brief and follow-up plan. - Makes outreach and follow-up more consistent—and easier to personalize. Good sales writing is specific, concise, and relevant. ChatGPT can draft first-pass emails, call…

Creating images with ChatGPT

Creating images with ChatGPT Generate and refine images using clear, descriptive prompts. ChatGPT can generate original images from plain-language prompts. You can iterate quickly—request variations, adjust composition or size, or explore new visual directions—and produce production-ready assets in minutes. This makes it easier to explore concepts, communicate ideas visually, and adapt existing assets for different audiences, formats, or channels. A good image prompt does not need to be long. In most cases, 1–3 clear sentences are enough. The goal is to help ChatGPT understand what the image is, how it should feel, and what it needs to accomplish. In practice, this means grounding the prompt in a few key details: the purpose of the image, the main subject, what is happening, where it takes place, and the desired visual style. If framing, lighting, or specific constraints matter, include those too.…

ChatGPT for finance teams

ChatGPT for finance teams Improve reporting, streamline planning, and communicate insights more clearly. Finance teams spend a lot of time turning incomplete inputs into something reliable—reconciling numbers, explaining variances, updating forecasts, and responding to business questions. The challenge is often the overhead such as organizing context, drafting narratives, and maintaining consistency across recurring work. ChatGPT helps reduce that overhead by structuring messy inputs, drafting first-pass outputs, and standardizing common workflows. It doesn’t replace finance judgment, but it reduces time spent on formatting, rewriting, and starting from scratch. - Helps you organize the work before you write or build. When you’re reviewing a spreadsheet export, a set of notes, and different explanations from stakeholders, the hardest part is often structuring the problem. ChatGPT can help you outline the questions to answer, the drivers to test, and the follow-ups to request—so you…

Healthcare

Healthcare AI resources for clinical workflows and decision support. This page brings together practical examples of how AI can support day-to-day clinical work. Whether you’re exploring early use cases or supporting teams already deploying AI, these prompts and guides are designed to help you move forward with confidence. Clinicians spend significant time searching for evidence, reconciling guidelines, and documenting care—time that could be spent with patients. ChatGPT for Healthcare is a secure workspace built for hospital providers and designed for HIPAA-compliant use, providing cited answers from trusted medical sources. It can support tasks like drafting clinical documentation, preparing prior authorizations, and summarizing patient information—helping reduce administrative overhead and improve focus on care. The prompt templates below illustrate how clinicians can use ChatGPT for Healthcare in common workflows.

Using skills

Using skills Create reusable workflows that guide ChatGPT through recurring tasks. Skills turn the way you already work into reusable workflows that ChatGPT can follow consistently—so you spend less time re-explaining steps, formats, and requirements, and more time getting to a solid result. If you’ve ever found yourself reusing the same prompt or pasting the same template again and again, skills are designed to fix that. A skill is a reusable, shareable workflow that tells ChatGPT how to do a specific task. Rather than starting from scratch each time, you define the process once so it can be applied reliably whenever the task comes up. A skill typically includes: - Name and description: Help ChatGPT recognize when the skill is relevant. - Workflow instructions: Step-by-step guidance for the worflow—usually written in a file called SKILL.md. - Resources: Supporting materials the…

Personalizing ChatGPT

Personalizing ChatGPT Customize ChatGPT’s behavior with instructions and memory to fit your needs. ChatGPT works best when you treat it less like a search box and more like a collaborator. It’s a new kind of tool—one that responds in a conversational way, can take on a “personality,” and adapts based on the guidance you give it. The more context and direction you provide, the more useful (and consistent) it becomes. In this section, you’ll learn two simple ways to personalize ChatGPT so it behaves more like a reliable teammate: Custom instructions and Memory. Custom instructions tell ChatGPT what it should know about you and how you prefer it to respond. These settings apply to new conversations until you change, disable, or remove them. Even small details can meaningfully improve results, such as: - Your role and responsibilities (“I lead customer…

Using custom GPTs

Using custom GPTs Build purpose-built ChatGPT assistants that follow your instructions, use your context, and streamline repeatable work. Some versions of ChatGPT let you build custom GPTs—purpose-built versions of ChatGPT designed for a specific task or workflow. Instead of starting from a blank chat each time, a custom GPT can follow your preferred format, use your team’s context, and produce more consistent outputs—whether you’re drafting content, analyzing recurring datasets, generating visuals, or answering common questions. Custom GPTs are powered by tailored instructions that define how the GPT behaves. You can also add knowledge (files you upload) and enable tools (such as web search, data analysis, or connected actions). The result: less re-explaining, less copy/pasting, and fewer “wait—what’s the context again?” moments. You can explore custom GPTs here(opens in a new window). A regular chat is well-suited for quick, one-off tasks—brainstorming…

Working with files in ChatGPT

Working with files in ChatGPT Upload and work with files to analyze, edit, and generate content. ChatGPT allows you to upload and work with files directly in your conversations. This means you can analyze spreadsheets, edit documents, summarize PDFs, or work with images without leaving your chat. - Start a chat with ChatGPT. - Upload your file by opening the tools menu and selecting “Add photos or files” (supported formats include CSV, XLSX, PDF, DOCX, JPEG, PNG, TXT, and more). 3. Ask a question or give a task, for example: - “Summarize the main findings in this report and call out any risks or open questions.” - “Visualize this sales data by region and highlight the biggest changes month over month.” - “Rewrite this document to be clearer and more concise, while keeping the same tone.” - “Extract the key…

ChatGPT for marketing teams

ChatGPT for marketing teams Plan campaigns, create content, and analyze performance faster with ChatGPT. Marketing teams often use ChatGPT to move smoothly from idea to brief to assets to launch—and then back again to review what worked. It helps bring scattered inputs into one place, turn them into clear messaging, and draft strong first passes of campaign content. Teams can also generate variations for testing and quickly summarize performance data into practical next steps. The result is less time spent starting from scratch or rewriting drafts, and more time focused on strategy, creativity, and execution. - Helps you think more clearly, faster. ChatGPT can take a messy starting point—notes, half-formed ideas, or lots of context—and turn it into a clear direction and next steps. It’s useful at both the beginning of a project, when you’re brainstorming or outlining, and at…

AI fundamentals

AI fundamentals Understand the basics of AI, including what it is, how it works, and how it’s used. Welcome! If you’re new to AI, you don’t need a technical background to get started. What helps most is a simple map of the landscape—so you can understand what AI systems can do, how they’re packaged, and how to choose the right tool for your needs. Artificial intelligence (AI) is a broad category of software that can recognize patterns, learn from data, and produce useful outputs. You’ve probably seen AI show up in everyday moments, like when: - Your map app reroutes you around traffic - Your bank flags a purchase as “unusual” - A customer support chatbot answers common questions AI is a category—not one single tool. Within that category are models: trained systems that learn from data and then apply…

Analyzing data with ChatGPT

Analyzing data with ChatGPT Explore, analyze, and turn data into clear insights and actions. Loading… ChatGPT can help you move from raw data to useful insights with minimal setup. You can upload a CSV or Excel file, paste in a table, or connect a data source (if supported in your workspace), then start asking questions in plain language. Instead of building formulas, pivot tables, or dashboards for every question, you can quickly explore data, clean up tables, generate simple visualizations, and extract key takeaways in a format that's easy to share. It’s especially useful early in the process—when you’re still figuring out what’s in the data, identifying anomalies, and deciding where to dig deeper. It also helps translate findings into summaries others can review and act on. - Start with the decision you’re trying to support. A simple frame is:…

ChatGPT for operations teams

April 10, 2026 OpenAI AcademyChatGPT for operations teams Bring structure and clarity to operational work with ChatGPT. Operations teams sit at the intersection of information and execution. ChatGPT behaves like an always-on chief of staff. It reduces coordination friction by turning fragmented inputs into decision-ready summaries, documenting outcomes as reusable SOPs, and reinforcing the operating rhythm with consistent updates and artifacts. The result is less time stitching information together and more time driving execution. Why operations teams use ChatGPT - Helps you turn scattered inputs into a clear set of next steps. Operational work often pulls from many sources—notes, trackers, messages, and updates. ChatGPT helps organize this into a simple structure: what’s known, what’s unclear, what needs a decision, and who’s responsible. - Makes status updates clear enough that people stop asking the same questions. Status updates often stall because…

Getting started with ChatGPT

Getting started with ChatGPT Learn the basics of using ChatGPT and how to begin your first conversation. ChatGPT is a conversational AI assistant that helps you think, write, and solve problems by understanding natural language and generating human-like responses in real time. ChatGPT is built on large language models, enabling it to assist with a wide range of tasks. Learn more about large language models in What is AI. Take a look at the video below to learn about the different parts of the ChatGPT interface. Open ChatGPT.(opens in a new window) A new chat is already waiting for you. To get started, simply enter a prompt. A prompt is the question or instruction you type or share with ChatGPT to start a conversation. It is usually text, but it can also be an image, audio, file. Your prompt guides…

ChatGPT for research

ChatGPT for research Use ChatGPT to move from questions to evidence-backed insights and decisions. Researching with ChatGPT helps you move from question to evidence to decision more quickly. You can use it to gather and synthesize information, compare sources, and produce structured reports that include citations—so your output is easier to trust and easier to share. It’s useful for both quick orientation and for deeper, multi-step investigations. Why use ChatGPT for research? - Turn a fuzzy question into a clear research plan and set of sub-questions. - Sift through many sources faster and capture the important details with citations. - Produce consistent deliverables such as briefs, memos, competitor tables, annotated bibliographies. - Identify gaps, contradictions, and weak signals early—before committing to a direction. ChatGPT offers two main approaches for research, depending on how deep you need to go: Search is…

Brainstorming with ChatGPT

Brainstorming with ChatGPT Generate ideas, organize thinking, and turn direction into actionable plans. ChatGPT can act as a structured thought partner. It helps you generate options quickly, organize ideas into clearer themes, and turn a rough direction into a plan you can execute. It’s especially useful when you’re starting from a blank page, working through many competing ideas, or creating a “first pass” before you bring others in. It won’t replace your context, expertise, or judgment—but it can make the thinking process faster, more consistent, and easier to share. Most brainstorming gets stuck in one of two places: not enough ideas, or too many ideas with no structure. ChatGPT helps by doing three things well: - Expands your option set: It can propose angles, experiments, messages, and alternatives quickly so you’re not starting from scratch. - Adds structure: It can…

OpenAI Full Fan Mode Contest: Terms & Conditions

OpenAI Full Fan Mode Contest: Terms & Conditions NO PURCHASE IS NECESSARY TO PARTICIPATE OR WIN. YOUR ENTRY INTO THE FULL FAN MODE CONTEST (THE “CONTEST”) CONSTITUTES ACCEPTANCE OF THESE CONTEST TERMS AND CONDITIONS. THIS CONTEST IS NOT SPONSORED OR ENDORSED BY INSTAGRAM, THE IPL, BCCI, OR ANY FRANCHISE. This Full Fan Mode Contest (the “Contest”) is organized and run by OpenAI via @chatgptindia on Instagram, and will run during the IPL 2026 season. The Contest is a skill-based competition where eligible participants must use the Full Fan Mode section on ChatGPT to generate an image, share it as an Instagram story, and tag @chatgptindia. All submissions (a “Submission”) will be evaluated by judges in accordance with these Terms & Conditions, and winners will be selected based on creativity and relevance, and may be eligible for prizes. By entering the…

The next phase of enterprise AI

I just wrapped my first 90 days with OpenAI and have had the opportunity to meet with hundreds of our customers. What has struck me most is their immense sense of urgency and readiness. I’ve spent my entire career at the intersection of technology and enterprise transformation, and yet, I have never seen this level of conviction spread so quickly and consistently across industries. These leaders recognize AI as the most consequential shift of their lifetime, and they’re asking us how to reinvent their companies around it. I also saw that conviction reflected in our business this quarter. Building on our consumer strength, enterprise now makes up more than 40% of our revenue, and is on track to reach parity with consumer by the end of 2026. Codex just hit 3 million weekly active users, our APIs process more than…

STADLER reshapes knowledge work at a 230-year-old company

STADLER reshapes knowledge work at a 230-year-old company Embedding ChatGPT across 650 employees to turn hours of knowledge work into minutes—scaling speed, quality, and decision-making company-wide. Results 125+ Custom GPTs created Results 30-40% Time savings on common knowledge tasks Results 2.5x Faster time to first draft on average Results >85% Daily active usage From industrial legacy to digital leverage STADLER is a family-owned company with more than 230 years of history, specializing in automated waste sorting plants for the global recycling industry. With over 650 employees operating worldwide, the company plays a critical role in helping countries advance their sustainability and circular economy goals. Under the leadership of Co-CEO Julia Stadler, the company has taken a forward-looking approach to modernization—embedding AI into everyday work as a core productivity layer. Since 2023, STADLER has pursued a clear principle: every employee working…

Inside our approach to the Model Spec

Inside our approach to the Model Spec As AI systems become more capable and widely used, we need a clear public framework for how they should behave. At OpenAI, we believe AI should be fair, safe, and freely available so that more people can use it to solve hard problems, create opportunities, and benefit in areas like health, science, education, work, and everyday life. We believe that democratized access to AI is the best path forward: not AI whose benefits or control are concentrated in the hands of a few, but AI that more people can access, understand, and help shape. That is a core reason why the OpenAI Model Spec exists. The Model Spec(opens in a new window) is our formal framework for model behavior. It defines how we want models to follow instructions, resolve conflicts, respect user freedom,…

New ways to learn math and science in ChatGPT

New ways to learn math and science in ChatGPT Explore concepts with interactive visual explanations. ChatGPT has quickly become one of the most widely used tools for learning. Each week, 140 million people use ChatGPT to help them understand math and science concepts alone. People also come to ChatGPT to explore new topics, work through homework problems, prepare for exams, and break down concepts they’ve always found difficult. For many learners, math and science concepts feel abstract and hard to understand. In a recent Gallup(opens in a new window) survey, more than half of U.S. adults said they struggle with math, and many parents reported they don’t feel confident helping their children learn it. Today, we’re making learning these concepts in ChatGPT even more interactive with new dynamic visual explanations. Starting with more than 70 core math and science concepts,…

Ensuring AI use in education leads to opportunity

Ensuring AI use in education leads to opportunity Our latest tools and resources can help educational institutions close AI capability gaps. Of the 900 million people who use ChatGPT each week, college-age adults are the biggest adopters among age groups. How they learn to use AI will increasingly shape their future opportunities, and education systems are uniquely positioned to help. Much of modern education was built to help students get ready for existing systems of work. But those systems are changing fast. Studies(opens in a new window) predict nearly 40% of the core skills workers rely on will change, largely because of AI. To thrive in this Intelligence Age, students need to build agency: the ability to learn continuously, solve hard problems, and create new economic opportunities for themselves with AI. Agency does not emerge from basic AI use alone.…

Understanding AI and learning outcomes

New tools for understanding AI and learning outcomes Advancing how AI’s impact is measured across learning environments Education is one of AI’s most promising frontiers. With tools like ChatGPT, personalized learning support can be available to any student, anywhere, at any time. But the education sector is still early in its understanding of the impact of AI on learning outcomes. Last year, our team set out to study the use of tools like study mode and found promising gains in student performance. But our research also raised an important question: how can we assess how AI influences a learner's progress over time, not just on a final exam? This is a broader ecosystem challenge. To-date, most research methods focus on narrow performance signals—such as test scores—and lack the ability to assess how students actually learn with AI in real-world settings,…

Generating State-of-the-Art GEMMs with TorchInductor’s CuteDSL backend

Introduction TorchInductor currently supports three autotuning backends for matrix multiplications: Triton, CUTLASS (C++), and cuBLAS. This post describes the integration of CuteDSL as a fourth backend, the technical motivation for the work, and the performance results observed so far. The kernel-writing DSL space has gained significant momentum, with Triton, Helion, Gluon, CuTile, and CuteDSL each occupying a different point in the abstraction-performance tradeoff. When evaluating whether to integrate a new backend into TorchInductor, we apply three criteria: (1) the integration does not impose a large maintenance burden on our team, or there is a long-term committed effort from the vendor; (2) it does not regress compile time or benchmarking time relative to existing backends; and (3) it delivers better performance on target workloads. CuteDSL satisfies all three. NVIDIA is actively developing CuteDSL and provides optimized kernel templates, which limits the…

How to make remarkable videos with Seedance 2.0

How to make remarkable videos with Seedance 2.0 Run Seedance 2.0 AI video used to be utterly bad. (We’ve all seen Will Smith eat spaghetti more times than we can count, so I’ll spare you.) Last year, however, we really began to see AI video take off with front-runners like Google’s Veo 3 series and Kling from Kuaishou. With each new model release, we inched toward improvements with prompt adherence, audio integration, and solving the “AI look.” Seedance 2.0 is the largest step change we’ve seen in months. You can make movies with this thing. A catastrophic collision between two massive space stations in low Earth orbit. Metal shears apart in slow motion as the stations grind into each other, sending a hailstorm of debris spiraling outward. Entire modules crumple like tin cans. Pressurized compartments blow out in violent bursts…

It's a big one

24th April 2026 This week's edition of my email newsletter (aka content from this blog delivered to your inbox) features 4 pelicans riding bicycles, 1 possum on an e-scooter, up to 5 raccoons with ham radios hiding in crowds, 5 blog posts, 8 links, 3 quotes and a new chapter of my Agentic Engineering Patterns guide. Recent articles - DeepSeek V4 - almost on the frontier, a fraction of the price - 24th April 2026 - Extract PDF text in your browser with LiteParse for the web - 23rd April 2026 - A pelican for GPT-5.5 via the semi-official Codex backdoor API - 23rd April 2026

Millisecond Converter

24th April 2026 LLM reports prompt durations in milliseconds and I got fed up of having to think about how to convert those to seconds and minutes. Recent articles - DeepSeek V4 - almost on the frontier, a fraction of the price - 24th April 2026 - Extract PDF text in your browser with LiteParse for the web - 23rd April 2026 - A pelican for GPT-5.5 via the semi-official Codex backdoor API - 23rd April 2026

Quoting Maggie Appleton

23rd April 2026 [...] if you ever needed another reason to learn in public by digital gardening or podcasting or streaming or whathaveyou, add on that people will assume you’re more competent than you are. This will get you invites to very cool exclusive events filled with high-achieving, interesting people, even though you have no right to be there. A+ side benefit. — Maggie Appleton, Gathering Structures (via) Recent articles - DeepSeek V4 - almost on the frontier, a fraction of the price - 24th April 2026 - Extract PDF text in your browser with LiteParse for the web - 23rd April 2026 - A pelican for GPT-5.5 via the semi-official Codex backdoor API - 23rd April 2026

Join us at PyCon US 2026 in Long Beach - we have new AI and security tracks this year

Join us at PyCon US 2026 in Long Beach—we have new AI and security tracks this year 17th April 2026 This year’s PyCon US is coming up next month from May 13th to May 19th, with the core conference talks from Friday 15th to Sunday 17th and tutorial and sprint days either side. It’s in Long Beach, California this year, the first time PyCon US has come to the West Coast since Portland, Oregon in 2017 and the first time in California since Santa Clara in 2013. If you’re based in California this is a great opportunity to catch up with the Python community, meet a whole lot of interesting people and learn a ton of interesting things. In addition to regular PyCon programming we have two new dedicated tracks at the conference this year: an AI track on Friday…

DeepSeek V4 in vLLM: Efficient Long-context Attention Apr 24, 2026 · 17 min read A first-principles walkthrough of DeepSeek V4's long-context attention, and how we implemented it in vLLM.

DeepSeek V4 in vLLM: Efficient Long-context Attention We are excited to announce that vLLM now supports the DeepSeek V4 family of models (deepseek-ai/DeepSeek-V4-Pro and deepseek-ai/DeepSeek-V4-Flash ). These models feature an efficient long-context attention mechanism, purpose-built for tasks involving up to one million tokens. While the new attention design may appear intricate on first reading, its underlying principles are straightforward once examined systematically. This blog post is organized into three sections: - Quickstart guide for serving DeepSeek V4 on vLLM - First-principles explanation of DeepSeek V4's new architectural design - Overview of our implementation approach and optimization challenges for this model on vLLM: hybrid KV cache, kernel fusion, and disaggregated serving. This represents our initial release of model support, and further optimizations are actively underway. We hope the technical explanation that follows can help the open-source community understand both the attention…

# fp8 ( 1 )

The State of FP8 KV-Cache and Attention Quantization in vLLM ·21 min read Long-context LLM serving is increasingly memory-bound: for standard full-attention decoders, the KV cache often dominates GPU memory at 128k+ contexts, and each decode step must read a large...

# kv_cache ( 1 )

The State of FP8 KV-Cache and Attention Quantization in vLLM ·21 min read Long-context LLM serving is increasingly memory-bound: for standard full-attention decoders, the KV cache often dominates GPU memory at 128k+ contexts, and each decode step must read a large...

# disaggregation ( 1 )

Next-Level Inference: Why Your Single-Node vLLM Setup Needs Prefill-Decode Disaggregation ·22 min read TL;DR: Prefill and decode fight over the same GPUs, causing ITL spikes under load. We show how to disaggregate them on a single 8-GPU MI300X node using AMD's MORI-IO connector — achieving 2.5x...

Next-Level Inference: Why Your Single-Node vLLM Setup Needs Prefill-Decode Disaggregation Apr 7, 2026 · 22 min read TL;DR: Prefill and decode fight over the same GPUs, causing ITL spikes under load. We show how to disaggregate them on a single 8-GPU MI300X node using AMD's MORI-IO connector — achieving 2.5x...

Next-Level Inference: Why Your Single-Node vLLM Setup Needs Prefill-Decode Disaggregation TL;DR: Prefill and decode fight over the same GPUs, causing ITL spikes under load. We show how to disaggregate them on a single 8-GPU MI300X node using AMD's MORI-IO connector — achieving 2.5x higher goodput compared to standard collocated serving on the same 8 GPUs, with stable token generation. Benchmark uses Qwen3-235B-A22B-FP8 at 8 req/s with 2000-token prompts and 1000-token outputs — see Table 3 and Experimental Details for full configuration. Introduction In our previous exploration of MoE optimization [1], we walked through distributing a massive model across an 8-GPU AMD Instinct MI300X node using Tensor, Pipeline, Data, and Expert Parallelism. In this blog, we show how Prefill-Decode disaggregation — enabled by AMD's MORI-IO — addresses this bottleneck, delivering higher goodput and more predictable performance without requiring a multi-node cluster.…

# engineering ( 1 )

Model Runner V2: A Modular and Faster Core for vLLM ·8 min read We are excited to announce Model Runner V2 (MRV2), a ground-up re-implementation of the vLLM model runner. MRV2 delivers a cleaner, more modular, and more efficient execution core—with no API...

# triton ( 1 )

vLLM Triton Attention Backend Deep DiveMar 4, 2026·10 min readThis article is adapted from a Red Hat hosted vLLM Office Hours session with Burkhard Ringlein from IBM Research, featuring a deep technical walkthrough of the vLLM Triton attention backend....

At 'AI Coachella,' Stanford Students Line Up to Learn From Silicon Valley Royalty

As thousands of influencers descended on southern California earlier this month for the annual Coachella Music Festival, a very Silicon Valley program dubbed “AI Coachella” was taking shape a few hundred miles north in Palo Alto. The class, CS 153, is one of Stanford’s buzziest offerings this semester, and like the music festival, it features a star-studded lineup of celebrities—in this case, not pop artists, but Big Tech CEOs. The course is co-taught by Anjney Midha, a former Andreessen Horowitz general partner, and Michael Abbott, Apple’s former VP of engineering for cloud services. The list of guest lecturers reads like a Signal group chat many VCs would pay to join: OpenAI CEO Sam Altman, Nvidia CEO Jensen Huang, Microsoft CEO Satya Nadella, AMD CEO Lisa Su, Anthropic philosopher Amanda Askell, and White House Senior Policy Advisor for AI Sriram Krishnan,…

Apple’s Next Chapter, SpaceX and Cursor Strike a Deal, and Palantir’s Controversial Manifesto

This week on Uncanny Valley, the team discusses what’s next for Apple as Tim Cook steps down from his role as CEO. They also go into the reasoning behind SpaceX and Cursor’s surprising deal, and why Palantir’s self-published manifesto drew a lot of heat online. Also, we discuss why some conspiracy theorists are leaving Trump’s side, and how a scammer created an AI-generated woman to attract and grift MAGA men. Articles mentioned in this episode: - Tim Cook’s Legacy Is Turning Apple Into a Subscription - MAGA Is Starting to Look Beyond Trump - This Scammer Used an AI-Generated MAGA Girl to Grift ‘Super Dumb’ Men You can follow Brian Barrett on Bluesky at @brbarrett, Zoë Schiffer on Bluesky at @zoeschiffer, and Leah Feiger on Bluesky at @leahfeiger. Write to us at [email protected]. How to Listen You can always…