Research / Knowledge Work
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.
The page clearly presents a real AI-powered product with a specific research workflow, concrete example use cases, and evidence of live access and documentation. It is useful for researchers and ML builders looking for an autonomous research assistant, and the page provides enough detail for a public listing.
The page does not show pricing, exact model capabilities, supported integrations, or a hands-on demo, and it is not clear how users interact with the system beyond joining the waitlist and reading docs.
Last evaluated just now. Current rank #17. Down 2 spots in the rankings.
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.
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.
