Research / AI Safety / Model Behavior
A research page on how censorship and behavior transfer during model distillation, with published models, data, evaluation code, and a benchmark called LineageEval.
The page clearly presents an AI research project with concrete artifacts: a study on distillation behavior, released models, a benchmark, evaluation code, and a GitHub link to the data. The visible text explains the experiment, the comparison setup, and the main finding, giving enough evidence for a useful directory listing.
The crawl cuts off before the full results and any reproducibility details such as exact repo structure, download links, or installation steps. It is also not obvious from the page whether the released assets are packaged for easy reuse or mostly research materials.
Last evaluated 31 days ago. Current rank #1556. 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.
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.
