---
title: "Dmitry Trifonov (@novibecoding) | Hashnode"
description: "Dmitry Trifonov (@novibecoding) writes on Hashnode. Read their latest articles and follow their work."
url: "https://hashnode.com/@novibecoding"
---

@novibecoding

# Dmitry Trifonov

@novibecoding · Joined August 2025

### [Host Setup for Qemu KVM GPU Passthrough with VFIO on Linux](https://novibecoding.hashnode.dev/host-setup-for-qemu-kvm-gpu-passthrough-with-vfio-on-linux?utm_source=hashnode&utm_medium=feed)

From “black magic” to reproducible results

14 min read · [novibecoding.hashnode.dev](https://novibecoding.hashnode.dev/host-setup-for-qemu-kvm-gpu-passthrough-with-vfio-on-linux?utm_source=hashnode&utm_medium=feed)

[Aug 26, 2025](https://hashnode.com/posts/host-setup-for-qemu-kvm-gpu-passthrough-with-vfio-on-linux/68ae2a9a0cd4d88bbe04c368)

### [Prompting DeepSeek. How smart it really is?](https://novibecoding.hashnode.dev/prompting-deepseek-how-smart-it-really-is-e34a3213479f?utm_source=hashnode&utm_medium=feed)

DeepSeek-R1 is a new and powerful AI model that is said to perform on par with leading models from companies like OpenAI but at a significantly lower cost. It also uses the new “Inference-Time Compute” (ITC) approach, like in OpenAI O1, which increas...

6 min read · [novibecoding.hashnode.dev](https://novibecoding.hashnode.dev/prompting-deepseek-how-smart-it-really-is-e34a3213479f?utm_source=hashnode&utm_medium=feed)

[Aug 20, 2025](https://hashnode.com/posts/prompting-deepseek-how-smart-it-really-is-e34a3213479f/68a6480fb3ba84ea6a277874)

### [How to develop your first LLM app? Context and Prompt Engineering](https://novibecoding.hashnode.dev/how-to-develop-your-first-llm-app-context-and-promptengineering-8c758dda849c?utm_source=hashnode&utm_medium=feed)

In this tutorial, we will develop a simple LLM-based application for rehearsal. We will supply text to the app, like a chapter of the book, and the app will ask us a question about the text, provide several answer choices, and check our answers. Dr. ...

10 min read · [novibecoding.hashnode.dev](https://novibecoding.hashnode.dev/how-to-develop-your-first-llm-app-context-and-promptengineering-8c758dda849c?utm_source=hashnode&utm_medium=feed)

[Aug 20, 2025](https://hashnode.com/posts/how-to-develop-your-first-llm-app-context-and-promptengineering-8c758dda849c/68a647c7fd195e396d8f6e7a)

### [Bug Bounty: NVidia Reset Bug](https://novibecoding.hashnode.dev/bug-bounty-nvidia-reset-bug-fd3c6c99d860?utm_source=hashnode&utm_medium=feed)

For RTX 5090 and RTX PRO 6000 Hey everyone — we’re building a next-gen GPU cloud for AI developers at CloudRift, and we’ve run into a frustrating issue that’s proven nearly impossible to debug. We’re turning to the community for help. On some of our ...

8 min read · [novibecoding.hashnode.dev](https://novibecoding.hashnode.dev/bug-bounty-nvidia-reset-bug-fd3c6c99d860?utm_source=hashnode&utm_medium=feed)

[Aug 20, 2025](https://hashnode.com/posts/bug-bounty-nvidia-reset-bug-fd3c6c99d860/68a64798b3ba84ea6a27786e)

### [UnSaaS your Stack with Self-hosted Cloud IDEs](https://novibecoding.hashnode.dev/unsaas-your-stack-with-self-hosted-cloud-ides-9cb41d7ea924?utm_source=hashnode&utm_medium=feed)

And save money on cloud GPUs for AI development I am a PC enthusiast and use it as much as possible. However, with the speed at which LLMs are growing in size, it is challenging to avoid the cloud for AI development. Many good GPU-enabled SaaS option...

5 min read · [novibecoding.hashnode.dev](https://novibecoding.hashnode.dev/unsaas-your-stack-with-self-hosted-cloud-ides-9cb41d7ea924?utm_source=hashnode&utm_medium=feed)

[Aug 20, 2025](https://hashnode.com/posts/unsaas-your-stack-with-self-hosted-cloud-ides-9cb41d7ea924/68a645b696423c61c9a5fc28)
