TypeSafe 详解 Jev：RLCD 训练的可靠决策模型，告别聊天优先
Jev and the System One Model: RLCD, intelligence/$, reliable AI, & the end of chat-first AI https://...
TypeSafe CEO 在播客里讲为什么 Jev 不做聊天、专攻软件内的可靠决策，连公开基准都拒绝跑，观点挺反共识。
Latent Space 播客本期对话 TypeSafe CEO，解释为什么 AI 能解决极难问题却难以自动化基础工作。其模型 Jev 被定位为 System One Model，用于在软件内部做可靠决策，而非聊天优先的交互。训练上采用 RLCD 方法，团队拒绝公开基准测试，并在 API 层移除拒答机制。他认为 System One Models 会影响 coding agents 和软件的开发方式，数据和选对任务比堆算力更关键，即使有 10 亿美元也不会从零预训练模型。
Jev and the System One Model: RLCD, intelligence/$, reliable AI, & the end of chat-first AI https://...
Jev and the System One Model: RLCD, intelligence/$, reliable AI, & the end of chat-first AI latent.space/p/jev @typesafeai CEO @CompleteSkeptic explains why AI can solve extraordinarily hard problems yet still fail to automate basic work, why Jev is built for reliable decisions inside software instead of chat, why TypeSafe rejects public benchmarks and refusals at the API layer, why data and the right task matter more than brute-force compute, how System One Models could reshape coding agents and software, and why even with $1 billion he wouldn’t pre-train a model from scratch. Your browser does not support the video tag. 🔗 View on Twitter 💬 4 🔄 10 ❤️ 27 👀 6346 📊 14 ⚡
