New Lab idler Raises $9M, Releases Real-World E-Commerce Agent Benchmark
ycombinator · x · 2026-08-20
Frontier data research lab idler announced a $9M seed round led by Paradigm with participation from Y Combinator.
They released ShelfLife, a dataset comprising 200 environments built from a decade of operational data of a live, profitable e-commerce store. It serves as a digital twin to evaluate agents in leadership roles. The leaderboard ranks Claude Opus 5 first with a 69% pass rate, followed by GPT-5.6 Sol and Fable 5.
Related event: Frontier Data Lab Idler Launches with $9M Seed Round(2 posts)→
More from Venture
- FT warns of 'Darwin moment' for AI borrowers as CoreWeave bonds sink to distress levels — firstadopter · 2026-10-16
- Founders who raised $10M-$50M two years ago are stuck in a quiet death spiral — SumitGup · 2026-10-16
- Anthropic commits $5M to help mathematicians navigate AI; Simons Foundation pledges $15M total — AnthropicAI · 2026-10-16
- NYC comptroller overseeing $325B pension asks Anthropic to delay IPO over safety concerns — rohanpaul_ai · 2026-10-16
- Musk endorses idea of an agent-first, US-only Amazon competitor — elonmusk · 2026-10-16
- Open-source Claude job-search system: scoring, tailored resumes and LinkedIn networking end to end — aranculleton · 2026-10-16