Stories by janpio

Pebble Appstore Archive

Benchmark Scores = General Capability and Claudiness

Claude.md: Best Practices for Optimizing with Prompt Learning

Cline-Bench: A Real-World, Open-Source Benchmark for Agentic Coding

The Droid Wars: Breaking up an AI‑orchestrated cyber fraud campaign

Hacker News Post Formatter – Preview Your HN Posts

Request For Comments: A secure contact import scheme for social networks

Visual Studio Code Private Marketplace: Your Team's Secure+Curated Extension Hub

Coding at work (after a decade away)

Burnout in Open Source: A Structural Problem We Can Fix Together

The productivity impact of coding agents

OpenHands Raised $18.8M to Build the Open Standard for Autonomous Software Dev

Does AI-Assisted Coding Deliver? A Study of Cursor's Impact on Software Projects

Peec AI raised $21M Series A to help brands win in AI search

Gemini 3 for developers: New reasoning, agentic capabilities

Mechanical Power by Linking Earth's Warmth to Space

Alloyed Agents: Combining LLMs to Improve AI Code Generation

What we learned building agents at Vercel

Measuring Political Bias in Claude

OpenAI's GPT-5.1 is an obsessive researcher, and Cline gives it focus

1
2
3
4
5
6
7
8