Research / Copywriting
A research code repository for studying how fine-tuning can trigger verbatim recall of copyrighted books in large language models. It includes preprocessing, fine-tuning, generation, and memorization-evaluation scripts, with setup notes and example data.
The page clearly describes an AI research project with concrete code for preprocessing books, fine-tuning models, generating outputs, and measuring memorization. The README gives enough usage detail, supported APIs/models, and setup steps to support a useful public listing.
The snapshot does not show the full evaluation section, license, or maintenance activity beyond a small commit history, so visitors cannot fully judge project maturity or whether the tooling works end to end.
Last evaluated 186 days ago. Current rank #892. Up 1301 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.
