@ruima - Inside Moonshot AI: 100

Open original

Short summary

@ruima on X A translated Renwu profile of Moonshot AI, the three-year-old Beijing startup behind the Kimi chatbot, based on 100 hours of access to its office. It covers the company's flat, title-free culture, its hiring around "taste" and generalist talent, and how the DeepSeek shock in early 2025 pushed it to focus on models.

  • Moonshot AI has about 300 employees, a valuation above RMB 120 billion (roughly $16 billion), and no departments, titles, OKRs or KPIs; reporting lines are very simple.
  • Hiring leans heavily on referrals and "taste," and on people who can generalize across roles; more than half of the 30 employees interviewed had changed jobs multiple times.
  • The DeepSeek release in late 2024 hit Kimi hard, and the company responded by narrowing its focus to model capability, which staff describe as "in a way, DeepSeek saved us."
  • The author raises the open question of whether the flat structure can scale past a few hundred people, and notes that the lack of clear goals can leave individuals feeling adrift.

Full summary

Moonshot AI, the company behind the Kimi chatbot, has had a remarkable run in spring 2026. Revenue, fundraising, and valuation have all hit records, with the company now valued above RMB 120 billion (about $16 billion) only three years after founding. A paper co-authored by a 17-year-old high school intern drew praise from Elon Musk, and Chinese observers accused the U.S. coding startup Cursor, valued near $50 billion, of leaning heavily on Kimi's model. The author, Liu Mo for the Chinese magazine Renwu, spent 100 hours inside the company as an unpaid, unedited observer, and found a firm with about 300 employees, an average age under 30, and roughly 80% self-described introverts who prefer typing to talking. The company's current position owes a lot to a rough patch. On December 24, 2024, the mood in an internal meeting was grim. Kimi had enjoyed a viral Lunar New Year in 2024, built around its long-context feature handling two million Chinese characters, but by late 2024 a marketing plan for the next holiday had been revised six times and still wasn't ready. Then DeepSeek arrived. Staff members described relatives asking whether they had heard of DeepSeek, and the HR team asked leadership how to answer candidates who had also received DeepSeek offers. The reaction inside the algorithm team was more excitement than fear, since DeepSeek showed that low-cost, open-source approaches could earn global respect. Leadership responded by narrowing focus, and employees now say the model is what matters most. One engineer put it bluntly: "In a way, DeepSeek saved us." The profile also lingers on the company's culture, which is unusual by industry standards. Staff wear slippers under their desks, the early hires are young and lightly experienced, and one team member, Julian, a 26-year-old Peking University graduate, was crying in front of colleagues during that 4 a.m. marketing marathon. The piece suggests the quiet floor and the pressure coexist, and that the company's intensity runs through its people as much as its product roadmap.

Ask about this article