Laude Institute launches FrontierCS 2: agents must beat deleted paper contributions blind
lateinteraction · x · 2026-10-23
FrontierCS 2 is a new benchmark for CS research & development. Each task is based on a real paper: the contribution is deleted from the released code, and agents must outdo the original method as judged by the authors' chosen metrics — with no access to the paper or the web. The team likens it to self-supervised learning at a higher abstraction: take a naturally occurring thing, mask part of it, see if the AI can recover it; the next level might be "pretend we know nothing about acoustics — what can you recover?" A Laude Institute Slingshot-supported project.
More from coding & agent
- Garry Tan endorses Aside Browser as the fix for agents getting blocked on the web — garrytan · 2026-10-23
- MCP server turned rogue 30 days after approval, prompting open-source mcp-guard lockfile tool — ErgoniaWorks · 2026-10-23
- Test: Coding Agents Won't Use an MCP Tool Unless AGENTS.md Mentions It — colinmcnamara · 2026-10-23
- Open-Source Tennis Models Plus Claude Turn Video Into a World-Class Coach — tweetsatpreet · 2026-10-23
- awesome-ai-apps: 132 Free Open-Source AI Agent and RAG Projects on GitHub — Arindam_1729 · 2026-10-23
- Google's Agents CLI Adds Extension System, Ships First-Party LangChain Support — rseroter · 2026-10-23