Купил мини‑ПК с приставкой «AI» ради локальной LLM. Что может NPU на самом деле
TL;DR. Я купил мини‑ПК с Ryzen AI 9 365, чтобы гонять большую локальную модель на NPU. Начал с Windows ради гибрида NPU+iGPU, к…
Programming
⚑ Сообщить о проблемеПоследние новости Programming от Tech News
Все темы
AI
agents
ai
api
architecture
automation
backend
beginners
career
database
devchallenge
devops
discuss
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
rust
security
showdev
testing
tutorial
typescript
webdev
When the AI Gateway Becomes the Weakest Link: Command Execution in LiteLLM's MCP Test Endpoints
When the AI Gateway Becomes the Weakest Link: Command Execution in LiteLLM's MCP Test Endpoints AI gateways have quietly become production infrastru…
Маршрутизация ИИ-моделей: когда одной модели недостаточно
Для разных задач требуются разные модели. Одни быстрее, другие дешевле. Есть те, что показывают лучшие результаты в анализе данных, и есть те, что л…
33,005 Internet-Reachable LiteLLM Gateways: Measuring the AI Gateway Attack Surface After CVE-2026-59822
33,005 Internet-Reachable LiteLLM Gateways: Measuring the AI Gateway Attack Surface After CVE-2026-59822 CVE-2026-59822 is an authentication bypass…
Terabytes of credentials leaked in massive supply-chain attack
The data was scraped and exfiltrated from 2,500 users of a compromised AI package.
Multi-Runtime Agents Without Fragmentation: The Control Plane Pattern
How teams move from "one API key per runtime" to "one gateway, any runtime" The Fragmentation Problem (July 2026) You've got a squad of coding agent…
CVE-2026-42271: How a Popular AI Gateway Became an RCE Vector — And What to Audit in Your Stack
The Vulnerability On May 8, 2026, BerriAI disclosed CVE-2026-42271 , a command-injection flaw in LiteLLM — one of the most widely deployed open-sour…
Airline and Transport Chatbot Compliance using LiteLLM + Microsoft ASSERT
Most production LLM assistants in airlines and transport systems fail not because of model capability, but because of policy violations under real u…
Lite-Harness SDK
AI harnesses are the new vendor lock-in. To swap across harnesses easily without rewriting your app, LiteLLM launched the Lite-Harness SDK . Run you…
The 5 Cost Traps That Will Quietly Bleed Your AI API Gateway Dry (And How to Fix Them)
In my last post, we talked about key cache invalidation — the silent production killer that turns your gateway into a 502 factory. Today I want to t…
LiteLLM CVE-2026-42271 Exploited in the Wild — AI Gateway Flaw Chains to Unauthenticated RCE
AI infrastructure is becoming a serious attack surface. The latest example is LiteLLM CVE-2026-42271 , a command injection vulnerability in BerriAI…
Barbacane vs Portkey and LiteLLM: picking an AI gateway in 2026
If you are picking an AI gateway in 2026, Portkey, LiteLLM, and Barbacane are all real options. They overlap enough to make the choice real, and the…