Research / AI Research Evaluation
A research post from Prime Intellect comparing 153 autonomous runs across 18 frontier models on a nanoGPT optimizer speedrun. It presents the setup, harness, results, and discussion around autonomous AI research performance.
The page is clearly about AI research and agent evaluation, with substantial visible evidence of the experiment, methodology, results, and limitations. It is specific, technical, and useful for people tracking autonomous research benchmarks or frontier model behavior.
It is a single research article rather than a standalone tool or API, so visitors cannot tell whether there is a reusable product, dataset download, or code package beyond the linked research repository.
Last evaluated 15 days ago. Current rank #1178. Down 2 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.
