AI/ML / Knowledge Base / Document Processing
A prototype company-brain product that turns 45,047 Enron emails into a cited wiki with time-aware facts, entity pages, and browsing by organization or internal system.
The page clearly describes an AI-powered product with a concrete output: a cited wiki built from a large email corpus, with facts tied to source emails and pages that expire when facts stop being true. It also shows practical product directions beyond the demo, including workflows, contacts, integrations, and an MCP server, plus enough visible detail to understand how the system works and what it produces.
This crawl shows a strong demo and methodology, but not the broader product limits: it is still unclear what sources beyond Enron mail the system supports, how a team would connect its own data, what editing/review tools exist, and whether there are pricing or deployment details for real customers.
Last evaluated 2 days ago. Current rank #231. Down 3 spots in the rankings.
Open-source demo for recognizing hand-object manipulation stages in everyday video, with installation steps, run commands, and a short explanation of the pipeline.
A browser game experiment where bots are controlled by neural networks and evolved with a genetic algorithm. The 2026 update adds shared server-side evolution, improved bot behavior, and a PHP/SQLite backend.
A detailed vLLM blog post explaining speculative decoding on AMD GPUs, with mechanics, supported drafting methods, configuration guidance, tuning advice, and benchmark discussion.
