Research / Knowledge Work
CTGT’s research post shows how deterministic LLM serving can still produce inconsistent pipeline outcomes, and introduces Concordance, an Apache 2.0 instrument for tracing where AI workflows diverge. The page includes the problem setup, benchmark details, findings, limitations, and a linked repo for reproduction.
This is a substantive AI research page with clear evidence of an AI-related tool and project context. It explains a real failure mode in LLM pipelines, describes what Concordance measures, gives benchmark and fix details, and points to a public GitHub repository with protocol, harnesses, and run data. That is enough for a useful directory listing.
The page is mainly a research write-up, so visitors still cannot tell the tool’s broader product shape, packaging, or integration surface from the crawl alone. There is no visible install guide, API reference, or screenshots of Concordance in use beyond the repo mention.
Last evaluated 5 days ago. Current rank #1647. 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.
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.
