Stay at the Frontier
Weekly dispatches covering the latest LLM research, Interactive Benchmark results, community puzzle highlights, and arena event announcements — for researchers and engineers who refuse to fall behind.
Join our growing community of AI researchers, engineers, and enthusiasts.
No spam. Unsubscribe any time. Weekly on Fridays.
Every issue is curated by the Interactive Hack team
The most important LLM papers from the week, summarized and contextualized for practitioners.
Latest results from our Interactive Benchmark arena — which models are leading and why.
Featured community-contributed puzzle of the week, with analysis and leaderboard highlights.
Browse the archive — everything is free to read
Speed, cost, and capability trade-offs across our community puzzle suite
The contamination problem, and how our community is tackling it with novel datasets
How we're building the most community-driven LLM evaluation platform
Our mission, the platform roadmap, and what's coming in 2026