Urgent.News

What's breaking now, across thousands of outlets.

AI

I built a PR reviewer that survived its own model being deprecated

This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend What I Built groq-pr-reviewer-net — a .NET 10 CLI that reads your git diff and returns a structured code review in your terminal, before you ever open the pull request. dotnet run -- --staged That's it. It reviews bugs and correctness, security, performance, and readability. The friend I built it for is the developer…

This article details the creation of a personal PR reviewer tool, named groq-pr-reviewer-net, which functions as a command-line interface (CLI) that analyzes a git diff and delivers a structured code review directly in the terminal. Developed in .NET 10, this tool assesses code for bugs, security, performance, and readability. The author built it for solo developers who lack a teammate or budget for a paid review bot.

The tool identifies issues like bugs, JSON parsing errors, and potential secret leakage in the diff. It is powered by an open-weight model from Groq, which allows for easy swaps or exchanges with another model at any time without any vendor lock-in. The reviewer can be run on Groq's free tier, ensuring no cost is incurred. Despite some false positives due to the model's knowledge cut-off, the tool aims to serve as a helpful second opinion rather than absolute truth.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

Gemma 4 QAT on One TPU v5e: What Runs and What Doesn't

This article provides a step by step guide to repacking Google's quantization-aware-trained (QAT) Gemma 4 weights for vLLM and serving them on one Google Cloud TPU v5e chip, with every build scored…

  • Gemma 4 models run efficiently on a single TPU v5e chip
  • 4-bit repack stores QAT grid values using int4 weights and activations
  • 8-bit repack shows slight speed advantage over 4-bit repack

Running DeepAgents in a Docker Sandbox, with no cloud keys

Agent frameworks are easy to pip install and surprisingly hard to run responsibly. The moment you give an agent a filesystem, a shell, and a network, you have handed arbitrary generated code the same…

  • DeepAgents framework allows creating agents with LangGraph library
  • Docker Sandbox Kit enables running DeepAgents without cloud credentials
  • Kit consists of four files and grants phase-scoped network policy

More from Friday 2 October →