Research / Knowledge Work
A research article from Applied Compute on how agentic, tool-using workloads differ from traditional LLM benchmarks, with production observations, workload profiles, and an open-source harness for replaying traces.
The page clearly presents a substantial AI research piece with concrete technical content: agentic workload characteristics, production deployment statistics, metrics for different deployment types, and an open-source harness for replaying agent traces. It is useful to AI builders working on inference engines, schedulers, or agent systems, and the crawl provides enough detail for a solid directory listing.
The crawl does not show the actual benchmark results, code repository, or download link for the harness, so a visitor cannot tell how to use it or reproduce the experiments from this page alone.
Last evaluated 118 days ago. Current rank #415. Down 107 spots in the rankings.
Primus is an autonomous AI researcher that hypothesizes, reads papers, writes code, runs experiments on compute, and drafts research papers. The page shows example tasks, published-paper claims, waitlist access, and positioning for ML research workflows.
An interactive dashboard that analyzes New York Times coverage since 2000 using the NYT Archive API, with views for reporters, beats, sections, subjects, geography, obituaries, and corrections.
An open benchmark and leaderboard for AI CAD agents, with 308 prompts across 20 categories and layered scoring for geometry, engineering, manufacturability, and cognition.
