Research / Knowledge Work
A research project exploring multi-agent LLM coordination in Pokémon Showdown. It compares talk modes, reports win rates and token costs, and frames the environment as a benchmark for studying collaboration between agents.
The page clearly presents an AI research project with a specific environment, method, and results. It explains the setup, the agent behavior, the talk modes being tested, and includes quantitative outcomes showing how communication affects performance and cost. That is enough evidence for a useful public listing.
The page does not show code, dataset access, or installation details beyond the linked GitHub repository, so visitors cannot tell how to run the environment or reproduce the experiments from the page alone.
Last evaluated 4 days ago. Current rank #1046. Down 6 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.
A research article benchmarking bot detection systems against scripted browsers, stealth browsers, and modern AI browsing agents, with comparative results across five detection products.
An open benchmark and leaderboard for AI CAD agents, with 308 prompts across 20 categories and layered scoring for geometry, engineering, manufacturability, and cognition.
