Stories by mustaphah

The visual feedback tool for coding agents

Agent Skills to help developers using AI agents with Supabase

METR AI Benchmark: Clarifying Limitations of Time Horizon

Scaling PostgreSQL to power 800M ChatGPT users

Claude Code plugin that rings your phone when a run needs you

Exercise can be nearly as effective as therapy for depression

Party of One for Code Review

FrontierScience Benchmark by OpenAI

Open Scouts: AI-driven web monitoring

A Rosetta Stone for AI Benchmarks

Study: Effects of LLMs versus Web Search on Depth of Learning

Stop Hiring for Languages. Start Hiring Great Engineers

Artificial Analysis: Claude Opus 4.5 is the #2 most intelligent model

Large-scale trial finds 4-day workweek improves employee well-being

mgrep: searching codebases with embeddings

Benchmarking LLMs at the Frontier of Physics

ChatGPT's social trait judgments align with human impressions

Show HN: Visual GraphQL Query Builder

The Learning Loop and LLMs

Is OpenAI becoming too big to fail?

1 2 3 4 5