# Neural Bits A technical publication for engineers designing, building, and deploying AI systems beyond demos. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## RAISE Summit 2026: What I Learned About AI, Robotics, Agents, and Infrastructure DevFeed: [RAISE Summit 2026: What I Learned About AI, Robotics, Agents, and Infrastructure]() Original publisher: [Read original article]() Author: Alex Razvant Published: 2026-07-25T07:00:53Z Content type: opinion Language: en Sources: [Neural Bits]() Topics: [Artificial Intelligence](), [Physical AI](), [Robotics](), [World models](), [Computer vision]() Tags: [ai](), [conferences](), [models](), [physical-ai](), [robotics](), [vision]() ### AI overview A personal account of RAISE and MACHINA Summit 2026 in Paris, covering conference themes and observations about AI, robotics, embodied AI, world models, perception, and the differences between language-oriented models and models used for robotic perception and action. ### Source excerpt Key takeaways from talks, demos, and conversations at RAISE and MACHINA conferences in Paris this year. ## The AI-Assisted Engineering Workflow I Use Day to Day DevFeed: [The AI-Assisted Engineering Workflow I Use Day to Day]() Original publisher: [Read original article]() Author: Alex Razvant Published: 2026-06-28T13:01:33Z Content type: tutorial Language: en Sources: [Neural Bits]() Topics: [AI-assisted coding](), [Loop Engineering](), [Test-driven development](), [Claude Code](), [codex](), [Production Engineering](), [coding]() Tags: [ai](), [claude](), [claude-code](), [codex](), [coding-agents](), [engineering](), [production](), [tdd](), [validation](), [workflow]() ### AI overview The article presents a controlled workflow for AI-assisted engineering with Claude, Codex, and other coding agents. It describes intake, task decomposition, test-driven development, bounded implementation, review gates, system validation, and sign-off while keeping the engineer involved throughout. ### Source excerpt How I structure intake, slicing, TDD, implementation, review gates, system validation, and signoff when working with Claude, Codex, and coding agents in production engineering work. ## Updates on an Axon AI Role, an AI Slide Deck, and an AI Systems Course DevFeed: [Updates on an Axon AI Role, an AI Slide Deck, and an AI Systems Course]() Original publisher: [Read original article]() Author: Alex Razvant Published: 2026-05-28T15:03:02Z Content type: article Language: en Sources: [Neural Bits]() Topics: [Artificial Intelligence](), [Machine learning](), [CUDA](), [foundation-models](), [systems]() Tags: [ai](), [cuda](), [ml](), [updates]() ### AI overview The author shares updates on a new L8 SWE/AI role at Axon, an expanding slide deck about GPUs and AI, and an AI Systems course, with an open live Q&A session planned for the next day. ### Source excerpt Updates on my new L8 SWE/AI role at Axon, the AI Slide Deck, and the production-focused AI Systems course + an open live session tomorrow. ## A few updates: the DGX Spark giveaway, new GPU inference slides, and my Vision AI Course DevFeed: [A few updates: the DGX Spark giveaway, new GPU inference slides, and my Vision AI Course]() Original publisher: [Read original article]() Author: Alex Razvant Published: 2026-04-11T13:03:07Z Content type: opinion Language: en Sources: [Neural Bits]() Topics: [GPU](), [Artificial Intelligence](), [DGX Spark](), [Inference](), [Nvidia](), [FIRST]() Tags: [ai](), [ai-training](), [dgx-spark](), [gpu](), [inference](), [models](), [nvidia](), [presentation]() ### AI overview The author shares updates about the completed DGX Spark giveaway organized with NVIDIA and a GPU and AI slide deck that is still in development. The presentation aims to explain how GPUs are used at scale for AI training and inference. ### Source excerpt What I've been working on behind the scenes, and what I'm preparing next. ## Building a Local AI Task Manager with PydanticAI and Ollama DevFeed: [Building a Local AI Task Manager with PydanticAI and Ollama]() Original publisher: [Read original article]() Author: Alex Razvant Published: 2026-03-22T14:03:18Z Content type: tutorial Language: en Sources: [Neural Bits]() Topics: [Ollama](), [Local AI](), [Pydantic](), [App](), [Large Language Model](), [Python](), [Code](), [Development]() Tags: [ai](), [code](), [dev](), [examples](), [guide](), [introduction](), [local](), [models](), [ollama](), [practical](), [tools]() ### AI overview A practical tutorial on building a local AI task manager with Ollama and PydanticAI. The application uses local language models and typed agent tools to handle tasks such as adding work, marking tasks complete, and listing overdue items. ### Source excerpt A practical introduction to agent-based architectures using typed models, tools, and runtime context in Pydantic AI. ## Win an NVIDIA DGX Spark by joining me for Virtual NVIDIA GTC 2026 DevFeed: [Win an NVIDIA DGX Spark by joining me for Virtual NVIDIA GTC 2026]() Original publisher: [Read original article]() Author: Alex Razvant Published: 2026-03-14T09:30:39Z Content type: article Language: en Sources: [Neural Bits]() Topics: [DGX Spark](), [Artificial Intelligence](), [Nvidia](), [GPU](), [Cloud]() Tags: [ai](), [cloud](), [dgx-spark](), [gpu](), [nvidia]() ### AI overview The article describes a Europe-only giveaway of one NVIDIA DGX Spark tied to attending a Virtual GTC 2026 session, newsletter subscription, and form submission. It also discusses the author's use of local GPU compute for iterating on AI systems. ### Source excerpt How to enter the giveaway - and what to expect if you're an AI engineer building on DGX Spark. ## Local LLM Inference : llama.cpp, GGUF, Quantizations and GGML Explained DevFeed: [Local LLM Inference : llama.cpp, GGUF, Quantizations and GGML Explained]() Original publisher: [Read original article]() Author: Alex Razvant Published: 2026-03-03T11:31:04Z Content type: tutorial Language: en Sources: [Neural Bits]() Topics: [llama.cpp](), [ggml](), [Inference](), [Large Language Model](), [Local AI](), [quantization]() Tags: [backend](), [cross-platform](), [efficiently](), [embedded](), [format](), [ggml](), [inference](), [llama-cpp](), [llm](), [local-llm](), [model]() ### AI overview A practical guide to local LLM inference with llama.cpp, explaining how the GGUF model format, GGML backend concepts, quantization, and inference workflows fit together for efficient execution on edge devices. ### Source excerpt Learn how the llama.cpp runtime, GGML backend concepts, and GGUF model format fit together for fast local inference across devices. ## The Engineer's Guide to AI-Assisted Productivity DevFeed: [The Engineer's Guide to AI-Assisted Productivity]() Original publisher: [Read original article]() Author: Alex Razvant Published: 2026-02-12T12:01:56Z Content type: article Language: en Sources: [Neural Bits]() Topics: [Artificial Intelligence](), [code productivity](), [coding](), [Pull Request](), [Claude Code](), [cursor](), [hooks](), [Obsidian]() Tags: [agent](), [ai](), [also](), [article](), [claude](), [claude-code](), [code](), [cursor](), [developer-productivity](), [guide](), [hooks](), [obsidian](), [open-source](), [productivity](), [pull-request]() ### AI overview This article argues that AI-assisted software development should prioritize design, planning, maintainability, and effective safeguards over raw lines of code. It presents habits involving Cursor Rules, Claude Code Skills, agent plugins, pull-request rules, reviews, hooks, and an Obsidian-based daily memory dump. ### Source excerpt Six habits that keep you fast and maintainable. Cursor Rules, Claude Code Skills, Agent Plugins, PR rules, non-nitpicky reviews, hooks, and Daily memory dump with Obsidian. ## Upcoming Livestream: GPUs for AI (Shaped by You) DevFeed: [Upcoming Livestream: GPUs for AI (Shaped by You)]() Original publisher: [Read original article]() Author: Alex Razvant Published: 2026-01-27T09:30:49Z Content type: article Language: en Sources: [Neural Bits]() Topics: [GPU](), [Artificial Intelligence](), [Hardware](), [CUDA](), [pcie](), [Nvidia](), [rocm](), [MLX](), [TensorRT](), [Google](), [groq]() Tags: [ai](), [cuda](), [google](), [gpu](), [groq](), [hardware](), [mlx](), [nvidia](), [pcie](), [rocm](), [tensorrt]() ### AI overview An upcoming livestream will discuss how GPUs and other accelerators support AI workloads. The author invites audience feedback to shape coverage of GPU hardware, PCIe, CUDA, ASICs, TPUs, LPUs, model optimization, and related technologies. ### Source excerpt You can choose the topics for a Live Session on GPUs in AI ## AI Engineers Should Focus on Systems, Architecture, and Production in 2026 DevFeed: [AI Engineers Should Focus on Systems, Architecture, and Production in 2026]() Original publisher: [Read original article]() Author: Alex Razvant Published: 2026-01-13T11:03:06Z Content type: opinion Language: en Sources: [Neural Bits]() Topics: [Artificial Intelligence](), [systems](), [agentic workflows](), [Inference](), [AI Strategy]() Tags: [2025](), [2026](), [agentic-workflows](), [ai](), [ai-engineer](), [architecture](), [compute](), [inference](), [production](), [reports](), [research]() ### AI overview This opinion article argues that AI engineers should prioritize system design, architecture, scale, inference, monitoring, testing, and core engineering fundamentals in 2026. It says most organizations remain in research or experimentation, and that production failures often stem from the engineering around AI models rather than the models themselves. ### Source excerpt A no-BS breakdown of where to invest your time, backed by real industry insights. ## Last article of 2025 - A Directional Update DevFeed: [Last article of 2025 - A Directional Update]() Original publisher: [Read original article]() Author: Alex Razvant Published: 2025-12-27T14:35:36Z Content type: article Language: en Sources: [Neural Bits]() Topics: [Building AI Systems](), [ai and ml](), [Computer vision](), [Code](), [C](), [C++](), [Python](), [Objective-C](), [Swift](), [iOS]() Tags: [2025](), [ai](), [applications](), [article](), [asus](), [building-ai-systems](), [c-plus-plus](), [code](), [computer-vision](), [ios](), [mac](), [objective-c](), [python](), [swift](), [update]() ### AI overview An end-of-year reflection on how the author's newsletter will change in 2026. The author connects early work and study choices with a gradual move into programming, AI, machine learning, and building AI systems, emphasizing that direction mattered more than speed. ### Source excerpt Reflecting on 2025, and how this newsletter is changing going into 2026 ## Unboxing the NVIDIA DGX Spark: First Impressions DevFeed: [Unboxing the NVIDIA DGX Spark: First Impressions]() Original publisher: [Read original article]() Author: Alex Razvant Published: 2025-12-20T14:15:48Z Content type: article Language: en Sources: [Neural Bits]() Topics: [DGX Spark](), [Nvidia](), [AI Development](), [Hardware](), [GPU](), [Benchmark](), [Multi-GPU]() Tags: [ai](), [ai-development](), [benchmarks](), [dgx-spark](), [gpu](), [hardware](), [multi-gpu](), [nvidia]() ### AI overview A hands-on review of the NVIDIA DGX Spark covering its unboxing, hardware design, software stack, intended audience, and benchmarks. The article argues that DGX Spark is designed as a local, DGX-aligned AI development system for building, testing, and validating models before scaling to cloud or cluster infrastructure, rather than as a high-end GPU replacement. ### Source excerpt The hardware, The Software components, benchmarks, target audience, and what it can do for AI Developers. ## An AI Engineer's Guide To Choosing GPUs DevFeed: [An AI Engineer's Guide To Choosing GPUs]() Original publisher: [Read original article]() Author: Alex Razvant Published: 2025-12-07T14:02:40Z Content type: tutorial Language: en Sources: [Neural Bits]() Topics: [GPU](), [Nvidia](), [Hardware](), [Machine learning](), [Artificial Intelligence](), [Inference](), [Large Language Model](), [Blackwell](), [Hopper](), [lora](), [NCCL](), [Kernel]() Tags: [ai](), [ai-engineer](), [architecture](), [blackwell](), [clusters](), [compute](), [data-center](), [deep-dive](), [gpu](), [guide](), [hardware](), [hopper](), [inference](), [llm](), [ml](), [nvidia](), [nvlink](), [pcie](), [software](), [technical]() ### AI overview A technical guide to choosing NVIDIA GPUs for AI workloads. It explains how GPU microarchitecture, memory subsystems, form factors, and interconnects affect capabilities, scaling, training, and inference, and compares consumer and data-center GPUs. ### Source excerpt A deep dive on technical Hardware and Software details of NVIDIA GPUs for AI Workloads. ## Recent Guides on AI Inference and FastAPI Backend Engineering DevFeed: [Recent Guides on AI Inference and FastAPI Backend Engineering]() Original publisher: [Read original article]() Author: Alex Razvant Published: 2025-11-29T14:02:54Z Content type: article Language: en Sources: [Neural Bits]() Topics: [AI Development](), [FastAPI](), [Inference Performance](), [backends](), [model-deployment](), [Pydantic](), [Retrieval Augmented Generation (RAG)]() Tags: [ai-engineer](), [ai-inference](), [deploy](), [fastapi](), [guides](), [inference](), [production]() ### AI overview A curated collection of recent guides for AI engineers. It highlights FastAPI and Pydantic practices for building maintainable AI and ML backends, along with inference engines and serving frameworks for deploying models in production across different scales and infrastructure. ### Source excerpt A curated list of the most actionable guides I've published in the past months. ## NVIDIA Nemotron Nano 2 VL 12B: Architecture and Improvements for Multimodal Reasoning DevFeed: [NVIDIA Nemotron Nano 2 VL 12B: Architecture and Improvements for Multimodal Reasoning]() Original publisher: [Read original article]() Author: Alex Razvant Published: 2025-11-22T14:58:39Z Content type: article Language: en Sources: [Neural Bits]() Topics: [Nemotron](), [multimodal](), [Nvidia](), [context window](), [long-context](), [Benchmark](), [Mamba](), [Transformer](), [AI Models]() Tags: [ai-ml](), [architecture](), [benchmark](), [context-window](), [long-context](), [mamba](), [ml-engineering](), [multimodal](), [nemotron](), [nvidia]() ### AI overview This article examines NVIDIA's Nemotron Nano 2 VL 12B, an open small vision-language model designed for document understanding, long-video comprehension, and multimodal reasoning. It discusses the model's architecture, encoders, training and inference improvements, reasoning modes, and reported benchmark performance, including a 128k-token context window. ### Source excerpt What makes NVIDIA Nemotron Nano 2 VL a breakthrough in small, fast, long-context visual reasoning. ## NVIDIA Nemotron Nano v2: Long-Context Reasoning and Efficient Inference in Smaller Models DevFeed: [NVIDIA Nemotron Nano v2: Long-Context Reasoning and Efficient Inference in Smaller Models]() Original publisher: [Read original article]() Author: Alex Razvant Published: 2025-11-15T14:47:33Z Content type: article Language: en Sources: [Neural Bits]() Topics: [Nemotron](), [Artificial Intelligence](), [Nvidia](), [long-context](), [model architecture](), [Inference](), [Open Source](), [Transformer](), [Large Language Model]() Tags: [ai-ml](), [inference](), [long-context](), [model-architecture](), [moe](), [nemotron](), [nvidia](), [open-source](), [reasoning]() ### AI overview This technical article examines NVIDIA's Nemotron Nano v2 Transformer-Hybrid models, focusing on their long-context reasoning, fast inference, and reported performance against larger open models. It also describes the broader Nemotron family's open models, datasets, and fine-tuning recipes for agentic AI systems. ### Source excerpt How NVIDIA's Nemotron Nano V2 SLM, built for long-context reasoning, fast inference, can compete with models 4-5x its size. ## What You Don't See: My Engineering Process Behind Each Article DevFeed: [What You Don't See: My Engineering Process Behind Each Article]() Original publisher: [Read original article]() Author: Alex Razvant Published: 2025-11-01T14:02:32Z Content type: article Language: en Sources: [Neural Bits]() Topics: [Building AI Systems](), [AI Strategy](), [Tooling](), [Notion](), [Obsidian](), [Markdown](), [Retrieval Augmented Generation (RAG)]() Tags: [ai](), [article](), [build](), [design](), [engineering](), [files](), [markdown](), [notes](), [obsidian](), [system-design]() ### AI overview The article explains the behind-the-scenes process of creating a practical AI/ML engineering newsletter. It describes capturing ideas, collecting notes and references, grouping them into topics, planning structure and visuals, building and revising projects, and writing about the results. It also emphasizes that engineering involves substantial reading, writing, design, and communication in addition to coding. ### Source excerpt My Working Desk. How I capture ideas, sketch System Design Diagrams, Write and Build AI Projects for this newsletter. ## The Complete Guide to Ollama: Local LLM Inference Made Simple DevFeed: [The Complete Guide to Ollama: Local LLM Inference Made Simple]() Original publisher: [Read original article]() Author: The AI Merge Published: 2025-10-25T13:02:36Z Content type: tutorial Language: en Sources: [Neural Bits]() Topics: [Ollama](), [Inference](), [Large Language Model](), [Command-line interface](), [Docker](), [Python](), [API]() Tags: [api](), [cli](), [docker](), [inference](), [llm](), [local](), [local-llm](), [ollama](), [python]() ### AI overview A practical guide to Ollama for local large language model inference. It covers Ollama's role in the LLM ecosystem, its architecture, model management and customization, Hugging Face model integration, an OpenAI-compatible API, Python usage, and Docker deployment. ### Source excerpt A deep dive into Ollama's architecture, going through model management, OpenAI API schema and local inference integrations with CLI, Docker and Python. ## A Partnership with NVIDIA and a Technical Walkthrough of Nemotron Models DevFeed: [A Partnership with NVIDIA and a Technical Walkthrough of Nemotron Models]() Original publisher: [Read original article]() Author: Alex Razvant Published: 2025-10-04T14:09:01Z Content type: article Language: en Sources: [Neural Bits]() Topics: [Nvidia](), [Nemotron](), [AI Models](), [Deep learning]() Tags: [ai-models](), [deep-learning](), [nemotron](), [nvidia](), [post-training](), [rag]() ### AI overview The author describes a partnership with NVIDIA and explains that it followed earlier coverage of NVIDIA technologies and interactions with NVIDIA teams. The article also includes a technical walkthrough of NVIDIA Nemotron models, discussing post-training techniques, compute kernels, and neural network layers. ### Source excerpt This means I can distill direct insights from NVIDIA experts! ## What AI Engineers Should Know About NVIDIA's AI Stack DevFeed: [What AI Engineers Should Know About NVIDIA's AI Stack]() Original publisher: [Read original article]() Author: Alex Razvant Published: 2025-09-27T13:30:30Z Content type: tutorial Language: en Sources: [Neural Bits]() Topics: [Artificial Intelligence](), [Nvidia](), [Software Engineering](), [AI Agent]() Tags: [ai](), [article](), [nvidia]() ### AI overview This article responds to a subscriber asking what to know about NVIDIA's AI stack. It distinguishes AI engineering from simply using models through APIs, argues for a pragmatic approach beyond AI-agent hype, and emphasizes end-to-end concerns such as infrastructure, optimization, evaluation, data pipelines, security, and production deployment. ### Source excerpt Answering a subscriber's question: "What should I know about NVIDIA's AI Stack?"