Scaling Coding-Agent RL to 32x H100s. 160% Improvement on Stanford's TBench
🌐Distributed systems
Flag this post
Parallel achieves 70% accuracy on SEAL, benchmark for hard web research
📊Performance Profiling
Flag this post
The APM paradox
📊Systems Monitoring
Flag this post
Octocode MCP – AI Researcher for Smart, Deep Multi-Repo Code Context
💻Programming languages
Flag this post
Lessons from GitHub
🔐Security Patterns
Flag this post
The Paranoid Guide to Running Copilot CLI in a Secure Docker Sandbox
💻Programming languages
Flag this post
Inline vs. Pipeline Ray Tracing
📊Performance Profiling
Flag this post
Show HN: Polyglot Docker dev environment setup – C/C++/Rust/Python
🌐Distributed systems
Flag this post
Show HN: Suites – modern unit tests framework for TypeScript back ends
💻Programming languages
Flag this post
Loading...Loading more...