Debugging ZORGAX: How We Traced an AI Agent Tool-Calling Loop from Open WebUI to Ollama
Debugging ZORGAX: How We Traced an AI Agent Tool-Calling Loop from Open WebUI to Ollama An evidence-first debugging story, with a reproducible test…
Testing & QA
⚑ Report a ProblemLatest Testing & QA news from Tech News
All topics
agents
ai
api
architecture
automation
backend
beginners
career
claude
cybersecurity
devchallenge
devops
discuss
javascript
llm
machinelearning
mcp
node
opensource
performance
productivity
programming
python
security
showdev
softwareengineering
testing
tutorial
typescript
webdev
Нейросеть написала PR, тесты зелёные, а поведение изменилось. Как я научил CI это ловить
Модель «упрощает» валидацию. Линтер молчит, тесты проходят, ревьюер видит аккуратный дифф в одну строку и жмёт Approve. Через неделю выясн…
Ollama vs LM Studio 2026: Ollama Wins for Devs
Verdict: in the ollama vs lm studio decision, Ollama wins for developers and automation, and LM Studio wins for everyone else. If you are scripting…
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…
Ollama's gemma4 renderer silently drops tool parameters named type or description, and the model invents a value
TL;DR : define a tool for a gemma4 model in Ollama with a parameter whose name is type , description , properties , required or nullable , and the m…
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…
Ollama's Responses API accepts previous_response_id, returns 200, and forgets the whole conversation
TL;DR : send previous_response_id to Ollama's /v1/responses and it is accepted, the reply is HTTP 200 with "status": "completed" and "error": null ,…
Build in the VM, Think on the Mac GPU: Debian 13 on Apple container With a Local Gemma 4
This article walks through building a Debian 13 machine under Apple's container CLI on an Apple silicon Mac, and then wiring that machine to a local…
Use host.docker.internal to reach local Ollama from Mule
Problem The flow failed with a connection refused error when the configuration used http://localhost:11434/v1 as the base URL. The MuleSoft Inferenc…
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…
Никто не просил — а я сделал банку робота-секретаря
Я люблю решать нерешаемые проблемы , делать людям жизнь легче, тестить гипотезы , создавать крутые продукты . Так меня позвали работать в Уралсиб, г…
I A/B tested my own system prompt: 24 generations, one clear win, one rule that did nothing | Flash Onyx 2.2
Flash Onyx is the model line behind FLASH , the local-first agent shell I work on. It is gemma4 plus a system prompt that turns it into an engineeri…
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…
Nine ways to talk to a local model
A nine-tool survey of local-model interfaces on one GPU: what worked, what silently failed, and why what sits between you and the model matters more…
I Point a Local LLM at Every Repo Before Opening It in My Editor
In May a "recruiter" sent me a take-home project for a Web3 role. Nice README, plausible Next.js structure, a real-sounding company. Buried in the b…
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…
My fresh OpenClaw install kept failing. The model wasn’t the problem.
I hit a failure pattern recently that’s way more common than people admit: install OpenClaw connect it to Ollama pull a decent local model test the…
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…
Local LLMs for an Infra-Monitoring Agent: The Ollama think Bug, and Why I Still Chose a Cloud Model
OpenClaw went from a weekend project to one of the most-starred repos on GitHub in under five months, and now everyone's using it to run their inbox…
AI agent python ollama: Build, Test, Deploy with FastAPI
I’ll show you how to get an ai agent python ollama up and running on your laptop, expose it through FastAPI, test it automatically, and push it to p…
Открытые LLM в продакшене: 8 выводов о llama.cpp, Gemma и Qwen
Об открытых языковых моделях написано много — и почти все статьи посвящены знакомству, в лучшем случае — «медовому месяцу» использования. Бенчмарки,…
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…
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…
Как я хакнул рынок труда: пишем свой ИИ-комбайн для автооткликов на HH.ru
Всем привет! Если вы хоть раз искали работу в IT за последний год, то знаете, что рынок беспощаден к новичкам. Нужно откликнуться на сотни вакансий,…
Building a Local-First Voice Copilot for the Shell with HoldSpeak and Ollama
The Promise: A Private, Voice-Activated Shell The dream of a voice-activated command line is compelling: speak a command, see it executed. But for m…
How I fixed silent Ollama failures in my local AI Assistant
How I fixed silent Ollama failures in my local AI assistant Neo-AI is an offline assistant with episodic memory, running entirely on-device using Ol…
Локальные LLM на Arch Linux и как увеличить скорость генерации в 20 раз
Приветствую всех читателей Хабра, в этой статье я хочу поделиться своим опытом в запуске локальных LLM, протестировать работоспособность и…
NeoBrain: A Local Alternative to Character.AI
🧠 NeoBrain: локальный аналог Character.AI Запусти ИИ-персонажей на своём ПК — без интернета, VPN и слежки. 🤔 Проблема Character.AI хорош, но: ❌ Забл…