Research / ML Experiment / Benchmark Result
A research blog post describing an open-source small transformer trained from scratch to reach 44% on ARC-AGI-1 at very low cost, with architecture notes, ablations, and pointers to code.
The page clearly documents an AI research result with concrete benchmark performance, a described training approach, ablations, and open-source code mention. It offers enough evidence for a useful public listing as a research/ML experiment page.
The crawl does not show the actual code repo, training setup details, or reproducible instructions, so a visitor cannot fully judge how to run or verify the result from this page alone.
Last evaluated 66 days ago. Current rank #2225. Up 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.
