Research / Paper
An arXiv paper on reducing LLM inference cost for web automation by compiling browser tasks into a deterministic JSON workflow and executing them without repeated model calls.
The page clearly describes an AI-focused research paper with a concrete method for LLM-driven web automation. The abstract provides enough evidence for a useful directory entry: problem statement, proposed architecture, cost claims, and evaluation results across several task types.
This is only the abstract page, so you cannot see the paper’s implementation, code, datasets, or whether a public project accompanies it. The snapshot also does not show reproducible instructions or an external repository link.
Last evaluated 85 days ago. Current rank #1839. Up 1 spot 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.
