Синтетическая эмпатия: как RAG, системные промпты и TTS инженерят привязанность к LLM-агентам
ELIZA в 1966-м заставляла секретарш просить не заглядывать в распечатки диалогов. Шестьдесят лет спустя компаньон-агенты на LLM делают то же самое,…
Architecture
⚑ Сообщить о проблемеПоследние новости Architecture от Tech News
Все темы
agents
ai
api
architecture
automation
aws
backend
beginners
career
database
devchallenge
devops
javascript
llm
machinelearning
mcp
news
opensource
performance
productivity
programming
python
react
security
showdev
softwareengineering
systemdesign
tutorial
typescript
webdev
Trail Journal: an offline nature walk companion built on Gemma
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built Trail Journal is a small two-script tool that p…
Optimizing for the 8GB Barrier: Strategic Model Selection for Local AI
Navigating the 8GB Hardware Landscape in 2026 For most developers, the dream of running a powerful Large Language Model (LLM) at home is not about s…
llama.cpp vs Ollama in 2026: Which Runtime Should You Run?
Ollama and llama.cpp are often compared as if they were rival inference engines. The real choice is between a managed model service and a toolkit yo…
KV Cache on 16 GB GPUs: Making Long Context Actually Fit
A model can advertise a 128K context window and still fail at 40K tokens on a 16 GB GPU. The architecture ceiling never promised that weights, KV ca…
Run LLMs Locally: Ollama Setup & Hardware Requirements
If you want to run LLMs locally, I recommend using Ollama to manage model weights and serve a local API. While you will need substantial hardware—ty…
Running the WUIC assistant on a local LLM: Ollama, an MCP server, and a free agentic VS Code
Our in-product RAG chatbot has two halves. The first is retrieval — hybrid BM25 + bge-m3 + a fine-tuned reranker, running locally as native .NET/ONN…
Fix Local LLM Quality: Context Stacking & Rope Freq Tweaks
This article was originally published on BuildZn . Everyone's running local LLMs now, which is great. But then they hit the wall: "Why does my 7B mo…
[Перевод] Qwen3.8-27B: лучший локальный LLM, который вы, вероятно, не сможете запустить
В этом месяце Alibaba выпустила две модели, и та, о которой все писали, оказалась не той, что мы ждали. Qwen3.8-Max — это API с 2,4 триллионами пара…
Moving Scheduled LLM Curation from Cloud APIs to Local Models
Scheduled LLM curation is the least glamorous agent workload you run. A cron job wakes up at 3am, reads a pile of memory, asks a model to dedupe it,…
A Local AI Pre-Commit Hook That Blocks Secrets Without Annoying You
My regex secret scanner once blocked a commit because a test file contained the string sk_test_EXAMPLE_KEY_DO_NOT_USE . The same week, a colleague o…
Function Calling With a Local LLM to Drive Foundry: Fuzz, Read, Repeat
The first time I let a local model drive Foundry unsupervised, it spent eleven turns trying to fix a fuzz test by renaming the test function. Not ch…
Qwen2.5-Coder vs DeepSeek-Coder for Solidity Review: What I Actually See Locally
I keep a folder of ten small Solidity contracts with bugs I planted myself: a classic reentrancy in a withdraw function, a missing access modifier o…
Ollama Model Loading RCE: Three Years of the Same Bug Class, One Self-Hosted LLM Runtime
TL;DR Ollama has shipped three remote-code-execution vulnerabilities in three years, all at the model-loading boundary. CVE-2024-37032 ("Probllama",…
Building an Autonomous Agent on an M1 Mac, by Choice
For about 3 months I've been running an autonomous agent — one that thinks up and writes its own social media posts and comments — unattended, 4 ses…
Does a Second GPU Increase Ollama's Context Window? (Quadro P2000 + RTX 3090 Tested)
TL;DR Short version: no. I dropped a much older GPU ( Quadro P2000, 5GB, Pascal, 2016 ) next to an RTX 3090 (24GB, Ampere) on the same box, ran the…
LLM Quantization Levels Compared: Q4_K_M vs Q8_0 vs FP16 [2026]
Originally published at kunalganglani.com — read it there for inline code, hero image, and live links. LLM Quantization Levels Compared: Q4_K_M vs Q…
Running a Whole RAG Agent Offline: LangGraph + Ollama + Embedded Qdrant (Zero API Keys)
Most RAG tutorials open with "set your OPENAI_API_KEY ." This one doesn't need it. In Part 1 I claimed the LLM and embeddings are behind a swappable…
I Built an AI Content Team That Posts to My Blog While I Sleep
I used to write blog posts the old way. Open a blank page. Stare at it. Write something. Rewrite it three times. Publish. Repeat every two weeks whe…
Hermes-Crew Hybrid: A Hybrid Architecture for Secure Multi-Agent AI Workflows
Hermes-Crew Hybrid: A Hybrid Architecture for Secure Multi-Agent AI Workflows I built a hybrid system that combines a central orchestrator (Hermes)…
Open Notebook Review: Self-Hosted NotebookLM Alternative
Originally published on andrew.ooo — visit the original for any updates, code snippets that aged out, or follow-up posts. TL;DR Open Notebook (by Lu…
Doubling Qwen3.6-27B on One RTX 3090: ollama llama.cpp + MTP, Lever by Lever (35.7 80.2 tok/s)
A reader on my last post said Ollama was leaving a lot on the table — that a tuned backend with multi-token prediction (MTP) could roughly double my…
Fitting WhisperX large-v3 + a 24B LLM on one 3090: a reproducible context-capping recipe
This is the technical, reproducible version of a fix I shipped on my own homelab. If you want the narrative version, that's on Medium. This one is t…
Do You Have a Homelab? Secure Your Local LLM Artifacts
We used to build homelabs around Linux servers, Docker containers, and NAS drives. It was about uptime, RAID levels, and monitoring CPU temps. Now,…
Local-first: a Model on Your Own Machine, Zero Cloud
This is the concrete, runnable walkthrough for Post 1 of the Portway series . The goal: stand up a single model behind an OpenAI-compatible endpoint…
I Tried Building a Complex Security Tool with a 1.5B Local Model — Here's What Broke
Problem: I had aider running on Lubuntu, three API keys configured, a detailed architecture diagram, and a clear goal — build a modular forensic dat…
Tesla P40 in a Homelab: 24GB of Inference on a Budget
The Tesla P40 is a seductive piece of hardware: 24GB of VRAM for a fraction of the cost of a modern RTX card. But after three weeks of fighting with…
Building a Private RAG System: Lessons from a Local-First AI Journal
Most AI apps quietly send your data to the cloud. DiaryGPT does the opposite — and this is the full technical story. The Problem With AI + Private D…
Using Ollama with the Laravel AI SDK: Run Local LLMs for Free
Originally published at hafiz.dev API costs add up fast during AI development. You prompt an agent 50 times debugging a tool, that's 50 API calls. Y…
I shipped local LLM features two months ago. Production never ran them once.
This is a submission for the Gemma 4 Challenge: Build with Gemma 4 Two months ago I shipped local-LLM features in TextStack — an open-source reader…