Hotspot: Linux `perf` GUI for performance analysis(github.com/KDAB) This project is a KDAB R&D effort to create a standalone GUI for performance data. As the first goal, we want to provide a UI like KCachegrind around Linux perf. Looking ahead, we intend to support various other performance data formats under this umbrella.
524 points by travisennis 4 days ago | 231 comments
GitHub Copilot: Meet the new coding agent(github.blog) We are excited to introduce a new coding agent for GitHub Copilot. Embedded directly into GitHub, the agent starts its work when you assign a GitHub issue to Copilot or prompt it in VS Code. The agent spins up a secure and fully customizable development environment powered by GitHub Actions.
Ask HN: Best on device LLM tooling for PDFs?(ycombinator.com) I've got very used to using the "big" LLMs for analysing PDFs<p>Now llama.cpp has vision support; I tried out PDFs with it locally (via LM Studio) but the results weren't as good as I hoped for.
272 points by flashblaze 7 days ago | 130 comments
Show HN: Online Compass(onlinecompass.in) An online compass show which way is north, east, south, and west using your device built-in sensors. It works just like a regular compass. You can use it to find directions without installing any apps.
Rethinking How I Deal With CLI Arguments (replacing getopt)(xnacly.me) This article covers the issues I found myself having while using getopt.h for a programming language bytecode interpreter pipeline I am currently working on (purple-garden1), implementation details for the replacement I wrote, examples of how to use the new solution and how I replaced the previous implementation with the new one using 6cl2.
MCP: How to Supercharge LLMs with Real-World Data, Tools and Memory(guptadeepak.com) Model Context Protocol is doing for AI what USB did for hardware and HTTP did for the web—creating a universal standard that exponentially expands capabilities. Understand how this innovation allows AI systems to access specialized tools without custom integration.